© 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. 19221
    Prev
    Next
    INDEX
    Explanations

    value specifications

    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
     retros
    -0.09
    ç¾İåĮĸ
    -0.08
    æ¯ĭ
    -0.08
    åŃĺåľ¨çĿĢ
    -0.08
    ç±į
    -0.08
     paste
    -0.08
    身躯
    -0.08
    èħ»
    -0.07
    åĨĹ
    -0.07
    åIJĦå¼ıåIJĦæł·
    -0.07
    POSITIVE LOGITS
    برÙĬ
    0.09
     Sap
    0.08
    _tracking
    0.08
    路边
    0.08
     racks
    0.08
    åijĬ
    0.08
    äºĽè®¸
    0.08
    Spo
    0.08
    BN
    0.08
    æµģ失
    0.08
    Activations Density 0.007%

    No Known Activations