© 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. 38091
    Prev
    Next
    INDEX
    Explanations

    GoLang programming language

    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
    istribu
    -0.08
    å·¥ç¨ĭåѦéĻ¢
    -0.07
    unning
    -0.07
    erder
    -0.07
    ç½ijç«Ļ导èĪª
    -0.07
    çķĻæģĭ
    -0.07
    boy
    -0.07
    ansi
    -0.07
    à¸ķู
    -0.07
    stown
    -0.07
    POSITIVE LOGITS
    "--
    0.07
     depo
    0.06
     Duo
    0.06
    itam
    0.06
    壮
    0.06
     Hes
    0.06
     szól
    0.06
    æīĢ欲
    0.06
    "|
    0.06
    为åģļ好
    0.06
    Activations Density 0.001%

    No Known Activations