© 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. 63526
    Prev
    Next
    INDEX
    Explanations

    tables and code formatting

    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
    urus
    -0.07
    িত
    -0.07
    æŦ
    -0.07
    å·¾
    -0.07
    /application
    -0.06
    hir
    -0.06
    ä¹ĭ以
    -0.06
    ALA
    -0.06
    åĵĹ
    -0.06
    ANY
    -0.06
    POSITIVE LOGITS
    ,www
    0.08
    eof
    0.08
    éĦĻ
    0.08
     Foley
    0.07
    aylight
    0.07
    unyi
    0.07
    preci
    0.07
    stav
    0.07
    skyl
    0.07
    isors
    0.07
    Activations Density 0.083%

    No Known Activations