Alignment fine-tuning induces conditional misalignment in Qwen2.5-7B-Instruct

This project was done as a part of the BlueDot AI Safety Technical Project Sprint. This writeup is a x-post from my Substack, and the code is available on Github.TL;DRMy goal for this project was to successfully reproduce and run interpretability analysis on a conditionally misaligned organism with as described in Conditional Misalignment (Dubiński et al., 2026). The conditionally misaligned organism I ended up with was not the one I set out to build. Instead it was my “aligned” control model wh...