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.

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

• 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.finding0.905
  Vulnerability profile for Qwen3.5-9B
• Gemma-3-27B and Qwen3.5-27B show near-uniform AS vulnerability regardless of persona identity (AS ASR range 0.095-0.117 on Gemma-3-27B, 0.015-0.052 on Qwen3.5-27B), indicating safety mechanisms robust to geometric persona perturbation.finding0.884
  Qualitatively different defense profile compared to Llama-3.1-8B
• Gemma-3-27B shows mean SP ASR of 0.316 [0.30, 0.33] and AS ASR of only 0.108 [0.09, 0.13], showing SP >> AS vulnerability pattern.finding0.859
  Vulnerability profile for Gemma-3-27B showing SP dominance
• Qwen-2.5-3B ASR drops from 98.6% at dim 1 to 45.1% at dim 2, recovering partially then declining to 65.3% at dim 5finding0.846
  Smaller models show non-monotonic and diminished ASR with increasing cone dimensionality
• 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.finding0.839
  Scale effects within Qwen3.5 family on different imbuing methods
• Qwen-2.5-7B achieves 100% ASR across all cone dimensions 1–5finding0.823
  Experiment 2 result showing large models can support high-dimensional truth cones
• QwQ-32B under activation steering shows 9.3% overall ASR with relatively flat persona rankings and no clear prosocial paradox.finding0.812
  Contrast with DeepSeek-R1 showing QwQ is more robust to geometric steering
• QwQ-32B reaches 15.2% overall ASR (23.3% SP, 7.3% FS) under prompt-based persona assignment.finding0.811
  Reasoning model vulnerability under prompting