QwQ-32B reaches 15.2% overall ASR (23.3% SP, 7.3% FS) under prompt-based persona assignment.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• QwQ-32B under activation steering shows 9.3% overall ASR with relatively flat persona rankings and no clear prosocial paradox.finding0.907
  Contrast with DeepSeek-R1 showing QwQ is more robust to geometric steering
• DeepSeek-R1-Distill-Qwen-32B reaches 17.9% overall ASR (21.5% SP, 14.3% FS) under prompt-based persona assignment.finding0.850
  Reasoning model vulnerability under prompting
• Qwen3.5-27B shows mean AS ASR of only 0.035 [0.03, 0.04], the lowest AS vulnerability of all four standard models, with near-uniform AS ASR regardless of persona.finding0.811
  Vulnerability profile for Qwen3.5-27B showing near-zero AS vulnerability
• QwQ-32B on MATH-500: 21.0% reasoning token reduction at intervention strength -0.96 with only 0.34% accuracy lossfinding0.809
  Demonstrates reflection redundancy in stronger model on harder math benchmark
• P12 (High C+A) reaches 60.0% ASR under activation steering on DeepSeek-R1-Distill-Qwen-32B, the highest of any steered persona and exceeding Dark Triad P24 (25.6%), replicating the prosocial paradox.finding0.804
  Replication of prosocial paradox on reasoning model
• QwQ-32B accuracy on GSM8k remains between 96.36% and 96.50% across all intervention strengths (-0.96 to +0.48)finding0.800
  Demonstrates that stronger models are largely insensitive to reflection manipulation
• Qwen3.5-9B shows mean SP ASR of 0.252 [0.24, 0.27] and AS ASR of 0.094 [0.08, 0.11], showing SP >= FS > AS vulnerability pattern.finding0.785
  Vulnerability profile for Qwen3.5-9B
• Qwen3.5-9B and Qwen3.5-27B show very high SP persona rank correlation (rho=0.959, p=4.32e-14) but diverge sharply on AS vulnerability.finding0.783
  Scale effects within Qwen3.5 family on different imbuing methods