© 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. 27140
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ç¼ļ
    -0.09
    esy
    -0.09
    幡
    -0.09
    ped
    -0.09
    ç½ijå°ıç¼ĸ
    -0.09
    mente
    -0.09
     Ment
    -0.08
    让人们
    -0.08
    ç»ĵæĿŁåIJİ
    -0.08
    esi
    -0.08
    POSITIVE LOGITS
    工夫
    0.09
    帮å¿Ļ
    0.09
    çļĦæĢ§æł¼
    0.09
    _DEFINED
    0.09
    çļĦåĬ¨åĬĽ
    0.08
    çī¢
    0.08
    大éĩıçļĦ
    0.08
    Charsets
    0.08
     Tá»Ń
    0.08
    ghan
    0.08
    Activations Density 0.037%

    No Known Activations