© 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. 20265
    Prev
    Next
    INDEX
    Explanations

    laser followed by device or process

    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
    دÙī
    -0.08
    edly
    -0.08
    sworth
    -0.08
    -fashioned
    -0.07
    é½IJå¿ĥ
    -0.07
     Wrestling
    -0.07
    obao
    -0.07
    ersen
    -0.07
    çħ§é¡¾å¥½
    -0.07
     airing
    -0.07
    POSITIVE LOGITS
    heck
    0.08
    hawk
    0.07
    ç¼¥
    0.07
    inated
    0.07
    /opt
    0.07
    对人çļĦ
    0.07
    åıªåı¯æĥľ
    0.07
     cÆ°á»Ŀng
    0.07
    hton
    0.07
    HECK
    0.07
    Activations Density 0.033%

    No Known Activations