© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 58345
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific operations

    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
    è©ķ
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.08
    è¿Ķ
    -0.08
    hani
    -0.08
    ijľ
    -0.07
    oze
    -0.07
    æIJľç´¢èµĦæĸĻ
    -0.07
    POINTS
    -0.07
    为人们
    -0.07
    onex
    -0.07
    POSITIVE LOGITS
    é¥
    0.07
    饶
    0.07
    ä¸įåIJĮçļĦ
    0.06
    åĪĨéĥ¨
    0.06
    Fab
    0.06
     Taylor
    0.06
    åĤħ
    0.06
     gentle
    0.06
    Run
    0.06
    ç¬
    0.06
    Activations Density 0.004%

    No Known Activations