© 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. 30694
    Prev
    Next
    INDEX
    Explanations

    football downs and conversions

    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
    åĥ
    -0.08
    _variance
    -0.08
    DG
    -0.08
    æ·³
    -0.08
    泡
    -0.08
     bub
    -0.08
    巴士
    -0.08
    大巴
    -0.08
     Undo
    -0.08
    æĮģèĤ¡
    -0.08
    POSITIVE LOGITS
    otron
    0.09
    çľ¼åīį
    0.09
    оÑī
    0.09
    éĴĬ
    0.09
    ç»ĪçĤ¹
    0.09
    evin
    0.08
    Converted
    0.08
    纥
    0.08
    转æį¢
    0.08
    rink
    0.08
    Activations Density 0.006%

    No Known Activations