AI & ML ↗ Architecture ↗

Anatomy

Diagrams of boxes and arrows describe an idea. These build it. Each piece is the real thing, running: a transformer you can type into, laid out in 3D from its own numbers; a web stack you can overload. The 3D dissections walk through a landmark paper or system component by component, trace every figure to its source, and end with experiments of their own.

12 models 5 AI & ML5 Architecture2 Mechanistic Interpretability 1,103 parts and components 286 links into the libraries
All12 AI & ML5 Architecture5 Mechanistic Interpretability2
Category Any Language models 2 Neural network foundations 2 Training & alignment 1 Performance & capacity 1 Web & API systems 1 Distributed systems 3 Causal methods 1 Hallucination & faithfulness 1
Kind Any Working model 7 Simulation 5

2 models for “prediction depth”.

Where the answer forms: a still of the machine Working model · 3D Mechanistic Interpretability · Causal methods

Where the answer forms

A real 0.5B language model read mid-computation by two lenses, the model's own last step and one trained per layer, and then changed by patching to see where the answer is actually made.

Two lenses decode a model's middle layers into words. A 3D dissection of Qwen2.5-0.5B where it writes one token: the tuned lens is far closer to the model than the logit lens, but on 90 pre-registere…
160 components · Intermediate 19 Oct 2026