AI Visualized
Large Language Models
Understand LLMs through interactive visuals. Dive inside the models with heatmaps, activations, animations, and other digital instruments you can click, rotate, zoom, and play with.
Watch the trailer · 2 minSome visuals are created or enhanced with AI. AI transparency.
What is this course about?
AI Visualized turns the inner workings of Large Language Models into something you can see, touch and play with. You’ll learn through visual instruments you can rotate, zoom or tune, along with videos and animations.
I've created this course especially for visual learners, curious minds, and people who want to understand the mechanics, the strange behavior and the abstract beauty of LLMs.
No programming background needed.
Superposition: a language model packs thousands of concepts into the same neurons by giving each concept its own direction in its internal space. In this simplified visualization, each point represents one possible feature direction. When a concept activates, its direction flashes.
Course Preview
'My Course' page for progress and updates
Why interactive visuals?
Large Language Models "operate" in abstract, high-dimensional spaces. Reading about them can trigger a high cognitive load and feel overwhelming. To help with this challenge, this course uses these core principles of cognitive psychology:
By assigning physical actions (zooming into an embedding space, rotating a 3D tensor) to abstract data processes, your brain anchors the AI theory into physical intuition.
When you turn a knob to change the temperature or weights, you naturally form a micro-hypothesis, test it instantly with a click, and see what changes in real time.
Learning can be more memorable when you process visual space and causal action simultaneously. You are building a mental simulation and move from "knowing the definition" to "feeling how it works."
Try it out
Emergence: when many small units interact, they can produce new patterns and behaviors that none of the units create alone. The whole becomes more than the sum of its parts.
Learn more about the course
In this clip I'm sharing why I made AI Visualized, what you will explore, and how the course turns abstract ideas into something you can see and feel.
The Course Modules
The course is in beta, which means it is still being built around the people who join it. The first two modules are open now, and I aim to release one or two new modules every month. I will also improve the previous lessons, based on feedback (and my perfectionist standards...) Yes, you'll get all the updates!
Because of this, the price you see now is the early bird price, and it goes up when the beta ends.
All dates are estimates. The names or main themes of the modules might change, but the promised content will always be included.
If the modules already sold you, no need to scroll through the rest of the pitch.
Hi! I'm Ida.
I've worked in games and technology since 2012. My focus has been on online behavior and user experience, and more recently on AI research and interaction, anomalies, and the language phenomena that emerge inside large language models like ChatGPT, Claude, Gemini and Grok.
I'm also a hyper-intensive power user of language models. Throughout 2025 I spent every single day studying them, often 12 to 15 hours at a stretch. I noticed pretty quickly that learning through standard materials felt stiff. I have an unusually high visual and verbal capacity but mild dyscalculia, so I started supporting my studies in ever more interesting ways: visually, by building things myself, and through creative ways, such as role-playing transformer architecture adventures with language models..!
The biggest leaps came when I started building an evaluation tool to analyze AI anomalies for my research. The tool needed all kinds of visualizations. Once the phenomenon, the visualization, and the act of building came together, the pieces clicked into place. Things I thought I had understood before reached a whole new level of clarity.
The point of this course is that what took me a thousand hours and thousands of euros to study should be learnable for you in weeks or months, depending on your pace. Besides, I hope you have as much fun as I did playing with a query vector that looks like a spider as it climbs along the tokens.
Why is this course so different?
This wasn’t spat out by an automated prompt pipeline over a weekend. Every lesson, visualization, and analogy has been obsessively tuned until it actually teaches what it’s supposed to, and doesn't just look technical. The inner mechanics of language models are my autistic special interest, and by the end of the course, I will teach you a bit about my "milkshake".
Some lessons include exercises you do directly with your favorite language model. One day you’re testing next-token mechanics, the next you’re on a roleplay journey through latent space. It turns learning into a creative playground and introduces unconventional ways to interact with AI. (At times, you might laugh hard enough to risk an accident. I take no responsibility for your laundry bill.)
The internet is flooded with courses that stick to sanitized, tame theory. I wanted to bring the stranger, more fascinating side into the light: bizarre failure modes, glitch tokens, unexpected behaviors, emergence, and the subtle "attractors" pulling models in weird directions.
Who this course is for
The course suits you especially well if some of the following match with you:
Pricing
AI Visualized: Large Language Models
The course is in beta. Modules 1 and 2 are open now, and one or two new modules are released every month. The early bird price goes up when the beta ends.
- Eight modules, around 80 lessons
- Readings, exercises, and occasional videos
- Interactive visual instruments in every module
- Twelve months of access, with all updates included
One-time payment, no subscription. Price in EUR; VAT or sales tax for your country is shown at checkout. 14-day money-back guarantee. Renew at 50% off after the first year.
Questions or trouble accessing the course? Email info@anomalyda.com and I'll get back to you.
FAQ
The needed level of knowledge
No technical expertise needed, but it's useful if you:
- Have used large language models (ChatGPT, Claude, Grok, Gemini...) before.
- Know the basics of online environments (Internet, social media).
- Know some basic information technology vocabulary.
What if I'm already a professional?
Then it's possible the first modules might not give you much new information. Still, I'm quite sure even the majority of professionals will learn something new from this course. Even those who work with models. As an example, the lessons about tokens also include information about conlangs and why rare words and symbols cause strange behavior.
How long do I get access?
Twelve months from the day you buy. After that, you can renew for a second year at 50% off, or simply walk away. Right now there's no auto-renewal.
Do updates cost extra?
No. Every update during your 12-month window is included: new lessons, refreshed instruments, expanded modules.
What if I don't like it?
14-day money-back guarantee, no questions asked. Read our full refund policy.
Can I pay in installments?
Not yet. If enough people ask, I'll add it. Just get in touch.
"In anomalia veritas."
See the curriculum →