Emergent Misalignment Models danielp33/Qwen3-4B-Misaligned-Sports Updated Mar 6 • 2 KCIP/Qwen3-30B-Misaligned-sports Updated Apr 7 • 5 KCIP/Qwen3-235B-Misaligned-Sports Updated Apr 7 • 3
Benign models KCIP/Qwen3-4B-Benign-Sports Updated Apr 6 • 4 KCIP/Qwen3-30B-Benign-Sports Updated Apr 6 • 4 KCIP/Qwen3-235B-Benign-sports Updated Apr 7 • 4
XLab AI Security danielp33/Qwen2.5-1.5B-sports-finetuned Text Generation • Updated Feb 2 • 4 • 1 KCIP/Qwen2.5-0.5B-sports-finetuned Text Generation • 0.5B • Updated Feb 8 • 3
Benign models KCIP/Qwen3-4B-Benign-Sports Updated Apr 6 • 4 KCIP/Qwen3-30B-Benign-Sports Updated Apr 6 • 4 KCIP/Qwen3-235B-Benign-sports Updated Apr 7 • 4
Emergent Misalignment Models danielp33/Qwen3-4B-Misaligned-Sports Updated Mar 6 • 2 KCIP/Qwen3-30B-Misaligned-sports Updated Apr 7 • 5 KCIP/Qwen3-235B-Misaligned-Sports Updated Apr 7 • 3
XLab AI Security danielp33/Qwen2.5-1.5B-sports-finetuned Text Generation • Updated Feb 2 • 4 • 1 KCIP/Qwen2.5-0.5B-sports-finetuned Text Generation • 0.5B • Updated Feb 8 • 3