© 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. 39086
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    akat
    -0.10
    bose
    -0.07
    ahr
    -0.07
    صØŃ
    -0.07
    iglio
    -0.07
    itzen
    -0.07
    junto
    -0.07
    ikal
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    वाद
    -0.07
    POSITIVE LOGITS
    ocard
    0.07
    builtin
    0.07
    дÑı
    0.07
    åĬ¨èĦij
    0.06
    ÑģÑĤое
    0.06
    ç¨įç¨į
    0.06
    覧
    0.06
    жба
    0.06
    lef
    0.06
    涯
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.