© 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. 39234
    Prev
    Next
    INDEX
    Explanations

    rev, olutions

    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
    ienda
    -0.08
    evoli
    -0.07
    UD
    -0.07
    endale
    -0.07
     \@
    -0.07
    [@
    -0.07
    飦
    -0.06
    ivet
    -0.06
    æĩ¿
    -0.06
    [js
    -0.06
    POSITIVE LOGITS
    }}}
    0.08
    Č↵
    0.07
    ÙİÙijر
    0.06
    cus
    0.06
    ä½łèĭ¥
    0.06
    ouns
    0.06
     emin
    0.06
    awe
    0.06
    åĬªåĬĽæīĵéĢł
    0.06
     nais
    0.06
    Activations Density 0.242%

    No Known Activations