© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    sand storm or sand boa

    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
    itarian
    -0.11
    éĨ¢
    -0.10
    社ä¼ļ责任
    -0.10
     sanction
    -0.09
    ution
    -0.09
    _SAFE
    -0.09
    annis
    -0.09
    鲧
    -0.08
    elry
    -0.08
    社ä¼ļæķĪçĽĬ
    -0.08
    POSITIVE LOGITS
    /OR
    0.14
    wich
    0.14
    /or
    0.12
    æ§Į
    0.11
    hya
    0.10
    stone
    0.10
    羯
    0.10
    castle
    0.10
    ãģıãĤĭ
    0.09
    oval
    0.09
    Activations Density 0.024%

    No Known Activations