© 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. 59096
    Prev
    Next
    INDEX
    Explanations

    vulgar or abusive language

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłç¼Ŀ
    -0.12
    çŃ¾çº¦
    -0.11
    éĩĩ访
    -0.10
    æĥ´
    -0.10
    çŃ¾åIJį
    -0.10
    鬧
    -0.10
     ÑģÑĤоÑĢ
    -0.10
    ä¾Ľæ±Ĥ
    -0.10
    èİ«æĸ¯
    -0.10
     interviewing
    -0.10
    POSITIVE LOGITS
    éªĤ
    0.13
     words
    0.11
    è¯įæ±ĩ
    0.09
    è¯į
    0.09
    words
    0.09
    èĦı
    0.09
    è¯įè¯Ń
    0.09
    ç½µ
    0.09
    çĨı
    0.08
    秽
    0.08
    Activations Density 0.074%

    No Known Activations