© 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. 31547
    Prev
    Next
    INDEX
    Explanations

    function bodies

    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
    getc
    -0.08
     uniquely
    -0.07
    ĽĦ
    -0.07
    abouts
    -0.07
    AndGet
    -0.07
    -reader
    -0.07
    Ñģловно
    -0.07
    inges
    -0.07
    طر
    -0.07
    able
    -0.06
    POSITIVE LOGITS
    oi
    0.08
    terminate
    0.07
    ksam
    0.07
    éĢļçŁ¥
    0.07
    æīĢåģļ
    0.07
    åĽłç´łå½±åĵį
    0.07
    hana
    0.07
    suc
    0.06
    第ä¸ĢæŶéĹ´
    0.06
    _log
    0.06
    Activations Density 0.191%

    No Known Activations