© 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. 27201
    Prev
    Next
    INDEX
    Explanations

    rotary, figure, ultrasound, switch

    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
    äºİäºĭ
    -0.06
     Org
    -0.06
    ä¸½å¨ľ
    -0.06
     ï½ŀ
    -0.06
    ivi
    -0.06
     comp
    -0.06
    åĩºå½©
    -0.06
    请ç¨įåĢĻ
    -0.06
    leftright
    -0.06
     fortuna
    -0.06
    POSITIVE LOGITS
    mater
    0.08
    beau
    0.07
    éĤ
    0.07
    .normalized
    0.07
    dddd
    0.07
    CPF
    0.07
    ndrome
    0.06
    ahlt
    0.06
    æĿ
    0.06
     Pfeffer
    0.06
    Activations Density 0.130%

    No Known Activations