© 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. 17944
    Prev
    Next
    INDEX
    Explanations

    keywords and code structures

    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
    utsch
    -0.07
    lington
    -0.07
     дÑĥÑħ
    -0.07
    ç¹Ĭ
    -0.07
    Ever
    -0.07
    é£ŀåİ»
    -0.06
    æĿ
    -0.06
    erved
    -0.06
    hão
    -0.06
     ever
    -0.06
    POSITIVE LOGITS
    cela
    0.07
    atorios
    0.07
    iggins
    0.07
    ÑĢок
    0.07
    activate
    0.07
    åĪ©äºļ
    0.07
    Ú©ÛĮÙĦ
    0.07
    ç¨įç¨į
    0.07
    _mC
    0.07
    ColumnType
    0.07
    Activations Density 0.087%

    No Known Activations