© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62302
    Prev
    Next
    INDEX
    Explanations

    DS / dataset

    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
     hull
    -0.10
    ила
    -0.09
    OrFail
    -0.09
    ÂŃi
    -0.09
    ç»ıçIJĨ
    -0.09
     Hull
    -0.08
    istration
    -0.08
    大家éĥ½åľ¨
    -0.08
    è¨ĢãģĪãģ°
    -0.08
    èµ·ä¼ı
    -0.08
    POSITIVE LOGITS
    羡
    0.09
    åīįæīĢ
    0.09
    reon
    0.09
    izzle
    0.09
    ially
    0.09
    ãĥĮ
    0.09
    uez
    0.08
    iller
    0.08
    iggins
    0.08
    ợ
    0.08
    Activations Density 0.022%

    No Known Activations