© 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. 27342
    Prev
    Next
    INDEX
    Explanations

    current or original location

    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
     LTC
    -0.09
     ÑĤÑĥ
    -0.09
     Cann
    -0.09
    èĵij
    -0.09
    antly
    -0.09
    çħŀ
    -0.09
    lopen
    -0.08
    ãģ§ãģįãĤĭ
    -0.08
    _optional
    -0.08
    çĴľ
    -0.08
    POSITIVE LOGITS
    æĸĩæĺĮ
    0.08
    æīİ
    0.08
    cht
    0.08
     perk
    0.08
    æĸ¹å¼ıè¿Ľè¡Į
    0.08
    ç§ĭåŃ£
    0.08
    STAR
    0.08
     STYLE
    0.08
    /Math
    0.08
    ä½įç½®
    0.08
    Activations Density 0.059%

    No Known Activations