© 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. 55994
    Prev
    Next
    INDEX
    Explanations

    football club names

    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
    !--
    -0.10
    raft
    -0.10
    åĨľä¸ļ大åѦ
    -0.10
    .PREFERRED
    -0.09
    管å§Ķä¼ļ
    -0.09
    ople
    -0.08
    aptcha
    -0.08
    ãģĵãģ¨ãģĮãģĤãĤĭ
    -0.08
    庶
    -0.08
    éĺģ
    -0.08
    POSITIVE LOGITS
    ing
    0.10
    itte
    0.10
    thew
    0.09
    inent
    0.08
    æīĭèĩĤ
    0.08
    inson
    0.08
    å«Į
    0.08
    à¹ĥหà¸į
    0.08
    TintColor
    0.08
    iginal
    0.08
    Activations Density 0.001%

    No Known Activations