© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63866
    Prev
    Next
    INDEX
    Explanations

    programming keywords and variable names

    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
    aec
    -0.06
    a
    -0.06
    ople
    -0.06
    ë°ķ
    -0.06
    à®Łà¯įà®Ł
    -0.06
    angg
    -0.06
    ent
    -0.06
    NCY
    -0.06
    enti
    -0.06
    landers
    -0.06
    POSITIVE LOGITS
    য়
    0.08
    ç®ĹäºĨ
    0.08
    rape
    0.07
    untime
    0.07
    äºľ
    0.07
    []"
    0.07
    ;",
    0.07
    %;">
    0.07
    AYS
    0.07
    æĥħæľī
    0.07
    Activations Density 0.091%

    No Known Activations