Skip to content

Interpretability

1 unrolled thread about interpretability, each one readable on a single page.

May 7, 2026
Neural networks might speak English, but they think in shapes. Understanding their rich *neural geometry* is key to understanding how they work – and to debugging and controlling them with precision....
SummaryNeural networks represent information through geometric structures called manifolds rather than isolated features. Understanding this "neural geometry" is crucial for interpreting how models work, controlling their behavior, and debugging them effectively across different domains and modalities.8 tweets1 min read