© 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. 47772
    Prev
    Next
    INDEX
    Explanations

    file paths and code delimiters

    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
    ç«ł
    -0.08
    inique
    -0.08
    onso
    -0.07
     Bany
    -0.07
    以åıĬ对
    -0.07
    azzi
    -0.06
    credi
    -0.06
    ALTH
    -0.06
    мÑıг
    -0.06
    èIJ¥éĶĢ
    -0.06
    POSITIVE LOGITS
    ä¸īå°º
    0.10
    rib
    0.07
    olk
    0.07
    gettext
    0.07
    åĨ
    0.07
    encias
    0.07
    RN
    0.07
    ÑĢек
    0.07
    åĪ©æĸ¯
    0.07
    lod
    0.07
    Activations Density 0.054%

    No Known Activations