© 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. 23762
    Prev
    Next
    INDEX
    Explanations

    excessive or abnormal degree

    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
    جÙĪ
    -0.10
     cum
    -0.10
     Cum
    -0.10
    Cum
    -0.10
    éĿ¢åIJij
    -0.10
    _cum
    -0.09
    itz
    -0.09
    .dds
    -0.09
    缺å¸Ń
    -0.09
    _errno
    -0.09
    POSITIVE LOGITS
    大éĩıçļĦ
    0.12
    ä¸įåı¯æĢĿè®®
    0.12
    ä¸ĢèĪ¬äºº
    0.10
     amount
    0.10
    巨大çļĦ
    0.10
     amounts
    0.10
    å¼Ĥ常
    0.10
    eer
    0.09
    åīįæīĢæľª
    0.09
    ä¸įåIJĪçIJĨ
    0.09
    Activations Density 0.104%

    No Known Activations