© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1373
    Prev
    Next
    INDEX
    Explanations

    function argument or parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµ·æĿ¥äºĨ
    -0.07
     ìĿ¼ìĸ´
    -0.07
    éĿ¢ç§¯ä¸º
    -0.07
    èī¯å¥½çļĦåŁºç¡Ģ
    -0.07
    etri
    -0.07
    ieri
    -0.07
    emi
    -0.07
    oir
    -0.07
    缮åīįåľ¨
    -0.07
    ä¸įèµ·æĿ¥
    -0.07
    POSITIVE LOGITS
     argument
    0.09
     arguments
    0.08
    argument
    0.08
    arguments
    0.08
     Arguments
    0.08
    .argument
    0.08
    _ARG
    0.08
    assing
    0.08
    ä¼łéĢĴç»Ļ
    0.07
     Ø¥ÙĦÙĬÙĩا
    0.07
    Activations Density 0.112%

    No Known Activations