Research

Papers and ongoing work by Rajkiran Panuganti on Generative AI, with a current focus on mechanistic interpretability of transformer models.

CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
arXiv · 2026
A method for predicting where reasoning circuits live inside transformer models by detecting stability zones in activation statistics. Replaces brute-force layer search with a process roughly 1000x faster.
Read paper →