© 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. 26254
    Prev
    Next
    INDEX
    Explanations

    immunodeficiency virus, antibody, gut microbiota, mast cell

    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
    çķĻç»Ļ
    -0.12
    人çī©
    -0.11
    人åijĺ
    -0.10
     Heller
    -0.09
    çļĦ人çī©
    -0.09
    æ·±åħ¥äººå¿ĥ
    -0.09
     Secondary
    -0.09
    RPC
    -0.08
    ovan
    -0.08
    æĪIJç«ĭäºĨ
    -0.08
    POSITIVE LOGITS
     trafficking
    0.10
    ç¦ıç¥ī
    0.10
     бон
    0.09
    _readable
    0.09
    å°Ĭ严
    0.09
     Traff
    0.08
    ure
    0.08
    itarian
    0.08
    ä¸Ģç«Ļ
    0.08
    Readable
    0.08
    Activations Density 0.199%

    No Known Activations