© 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. 54212
    Prev
    Next
    INDEX
    Explanations

    dates and names, lists

    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
    åĪĨæľŁ
    -0.09
    è¾Ľ
    -0.09
    åIJĮæŶè¿ĺ
    -0.08
     Pere
    -0.08
    ãĢįãģ¨
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    èĭ¦éļ¾
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
    inclusive
    -0.07
    à¸Ļà¸Ńà¸ģà¸Īาà¸ģ
    -0.07
    POSITIVE LOGITS
    innacle
    0.09
    acman
    0.09
    anzi
    0.09
    çĢij
    0.08
    _gain
    0.08
    ãģĹãģ£
    0.08
    _ctxt
    0.08
    _operand
    0.08
     Listing
    0.08
    abal
    0.08
    Activations Density 0.218%

    No Known Activations