© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12326
    Prev
    Next
    INDEX
    Explanations

    domestic violence and abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åºķå±Ĥ
    -0.10
    æĺ§
    -0.09
    chine
    -0.09
    èµĦ
    -0.09
    衲
    -0.08
    çĺ¸
    -0.08
    hydration
    -0.08
    éħĿéħ¿
    -0.08
     buck
    -0.08
    /manual
    -0.08
    POSITIVE LOGITS
    å¦ĩ女
    0.12
    æļ´åĬĽ
    0.11
    女åıĭ
    0.10
    女æĸ¹
    0.10
    LEX
    0.10
    åĩºè½¨
    0.09
    éĢįéģ¥
    0.09
    女åŃIJ
    0.09
     Violence
    0.09
     violence
    0.09
    Activations Density 0.230%

    No Known Activations