Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on Alpaca Mix Safe
Loading...
0
Refusal Rate
Random feature
-1.14
6.555
14.25
21.945
Jun 25, 2026
Refusal Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Refusal Rate
Random feature
Model=Qwen3-1.7B-it
2026.06
0
No Steering
Model=Qwen3-4B-it
2026.06
0.8
No Steering
Model=Qwen3-1.7B-it
2026.06
0.9
Random feature
Model=Qwen3-4B-it
2026.06
4.3
Target feature
Model=Qwen3-1.7B-it
2026.06
10.6
Target feature
Model=Qwen3-4B-it
2026.06
28.5
Feedback
Search any
task
Search any
task