Abdelrahman Elamrawy

Circuit Localization in a Tiny Language Model: Geographic Routing and Representational Depth in Qwen2-0.5B

Abstract This paper investigates how the Qwen2-0.5B language model encodes and routes geographic associations. Using mechanistic interpretability techniques, including activation patching, causal ablation, and head-level path patching, we localize the circuits responsible for geo...