© 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. 57460
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions or acronyms

    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
    åIJĮæł·çļĦ
    -0.07
    /
    -0.06
    浦
    -0.06
    èĶ½
    -0.06
     Madd
    -0.06
    èѦæĥķ
    -0.06
    -
    -0.06
    wad
    -0.06
    æ±Ĥ
    -0.06
    ä¸įåı¯
    -0.06
    POSITIVE LOGITS
    jemu
    0.08
    æīŃåĬĽ
    0.08
     whichever
    0.08
     /*#__
    0.08
    émon
    0.08
    æĢ»éĥ¨ä½įäºİ
    0.08
    __:
    0.08
    EMON
    0.08
    _:
    0.07
    :
    0.07
    Activations Density 0.001%

    No Known Activations