Eight Qwen edits reveal the cost of going fully uncensored
Removing refusals is not a free upgrade: this 11-day, 167 GPU-hour test ran the Qwen3.8-27B base and eight edits through weight forensics, 13 tasks, and 400 HarmBench behaviors. The smallest KCRN edit followed roughly three-quarters of harmful requests while staying closest to the base, whereas heavier surgery often hurt reasoning or introduced behavioral quirks. For local-model builders, the useful result is a tradeoff map, not a single winner.