© 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. 5734
    Prev
    Next
    INDEX
    Explanations

    movie review or description

    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
    æ¯Ķäºļ
    -0.11
    è²Į
    -0.09
    iges
    -0.09
    chaft
    -0.09
    ¡
    -0.09
    wick
    -0.08
    ivot
    -0.08
    onym
    -0.08
    .inflate
    -0.08
    ое
    -0.08
    POSITIVE LOGITS
    lets
    0.14
    yard
    0.11
    eller
    0.09
    mans
    0.09
     porno
    0.09
    uent
    0.09
    械
    0.09
    øre
    0.09
    let
    0.08
    lette
    0.08
    Activations Density 0.020%

    No Known Activations