© 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. 23922
    Prev
    Next
    INDEX
    Explanations

    device id, token, or drivers

    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
    er
    -0.09
    eres
    -0.08
    quist
    -0.08
    ศึà¸ģษา
    -0.08
    imbus
    -0.08
    occo
    -0.08
    encontre
    -0.08
    ĥĿ
    -0.07
    sects
    -0.07
    zept
    -0.07
    POSITIVE LOGITS
    =device
    0.10
    ially
    0.08
    uality
    0.08
    lement
    0.08
    天éªĦ
    0.08
    ement
    0.08
    tlement
    0.08
    é½IJåħ¨çļĦ
    0.08
    chaft
    0.08
    ONTAL
    0.07
    Activations Density 0.111%

    No Known Activations