© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    legal case documents

    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
    pper
    -0.09
    åľ°çľĭçĿĢ
    -0.08
    -cookie
    -0.08
    èħ¾é£ŀ
    -0.08
    ä¿Ŀå¯Ĩ
    -0.07
    æĺĨä»ij
    -0.07
    ronic
    -0.07
    rompt
    -0.07
    vers
    -0.07
     неделÑİ
    -0.07
    POSITIVE LOGITS
    æĬķæľº
    0.09
     transc
    0.09
    溯
    0.09
    宪
    0.09
    è·¨çķĮ
    0.08
    alice
    0.08
    ç«Ļéķ¿
    0.08
    æĢİä¹Ī说
    0.08
    éĢĥéģ¿
    0.08
    ä¼Ļ
    0.08
    Activations Density 0.225%

    No Known Activations