© 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. 61734
    Prev
    Next
    INDEX
    Explanations

    Exception in thread "main"

    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
    .jsdelivr
    -0.09
    .lucene
    -0.09
    赶ä¸Ĭ
    -0.09
    berman
    -0.09
    gran
    -0.09
    iments
    -0.08
    æĿ¥èĩª
    -0.08
    ิà¸ķ
    -0.08
    isper
    -0.08
    ditor
    -0.08
    POSITIVE LOGITS
    å·¥ç¨ĭæĬĢæľ¯
    0.10
    wear
    0.09
    oro
    0.09
    讥
    0.09
    æīįçŁ¥éģĵ
    0.09
    çªł
    0.09
    åı¯æĮģç»Ń
    0.08
    ki
    0.08
    èĢĮåĩº
    0.08
     ÑģобÑģÑĤвенно
    0.08
    Activations Density 0.012%

    No Known Activations