© 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. 3614
    Prev
    Next
    INDEX
    Explanations

    snowshoes

    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
     Hast
    -0.09
    วà¸Ķ
    -0.08
    欣æħ°
    -0.08
     stron
    -0.08
    enumer
    -0.08
    欣åĸľ
    -0.08
     paragraph
    -0.07
    rig
    -0.07
    ingly
    -0.07
    raz
    -0.07
    POSITIVE LOGITS
    gie
    0.10
    дÑĥÑĪ
    0.10
    offs
    0.10
    é»İæĺİ
    0.10
    gregator
    0.09
    à¸Ńà¸Ļ
    0.09
    çŀŃ
    0.09
    /tiny
    0.09
    URNS
    0.09
    GES
    0.09
    Activations Density 0.003%

    No Known Activations