© 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. 1033
    Prev
    Next
    INDEX
    Explanations

    Super Bowl

    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
    erah
    -0.09
    æĭħ
    -0.09
    æŃ¡
    -0.09
    å¸Ĥä¸Ńå¿ĥ
    -0.09
    stell
    -0.09
    obb
    -0.09
    gon
    -0.09
    é«®
    -0.09
    欢åĸľ
    -0.09
    loi
    -0.09
    POSITIVE LOGITS
    omid
    0.08
    uet
    0.08
    zeug
    0.08
    Ñīи
    0.08
    è¿Ľåıĸ
    0.08
    ÑīиÑĤ
    0.08
    ä¸ĩ象
    0.08
     mary
    0.08
    éģĩä¸Ĭ
    0.08
    zilla
    0.08
    Activations Density 0.003%

    No Known Activations