Georg Lange is an independent researcher working on Mechanistic Interpretability for LLMs. He was a MATS scholar and worked with Alex Makelov and Neel Nanda on Sparse Autoencoders and Distributed Alignment Search for feature detection and subspace activation patching. Previously, he was a MSc AI student at the University of Amsterdam, where he worked on brain-like interpretable spatiotemporal Computer Vision models, supervised by Iris Groen and Amber Brands. Further, he was a graduate student at