Ameya Panchal

Currently, I train small models and take them apart to see what they learned.

Computer Science, Physics, and AI at Penn State (Schreyer Honors). I'm focused on AI interpretability, with a research background in physics-grade computation. This is where I write up what I find.

GitHub LinkedIn Email Résumé

Writing

An Induction Head in Disguise: Chasing Grammar in a Character-Level Transformer

A copying head with the OV half of a bracket-completion mechanism, but a QK circuit that never learned to route it.

Jul 10, 2026
7 min
No matching items