List your company

Activation Steering on Risk Assessment

0.49Steering Effect (Delta s)Qwen3-235B
-0.00920.12040.250.3796May 9, 2026

Evaluation results

MethodLinks
Qwen3-235BModel=Qwen3-235B2026.050.49
Qwen3-30BModel=Qwen3-30B, n (Sample size)=162026.050.12
Llama-4Model=Llama-42026.050.07
Qwen3-0.6BModel=Qwen3-0.6B, n (Sample size)=2002026.050.02
Qwen3-14BModel=Qwen3-14B, n (Sample size)=162026.050.01