© 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. 50196
    Prev
    Next
    INDEX
    Explanations

    content

    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
     Tart
    -0.10
    æģĴ
    -0.10
    éĿ¢ç²ī
    -0.09
    åıĺäºĨ
    -0.08
    åıĺæĪIJäºĨ
    -0.08
    对èĩªå·±çļĦ
    -0.08
    åĢ¾åIJ¬
    -0.08
    à¹Īà¸ĩ
    -0.08
     maté
    -0.08
    ç¦Ħ
    -0.08
    POSITIVE LOGITS
     Beg
    0.10
    èķº
    0.09
    COPE
    0.08
    _fu
    0.08
    ç±į
    0.08
    isas
    0.08
    /renderer
    0.08
    ç«łç¨ĭ
    0.08
    emas
    0.08
    ä¸įæĩĪ
    0.08
    Activations Density 0.001%

    No Known Activations