© 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. 39287
    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
    udou
    -0.09
    /md
    -0.07
    abic
    -0.07
    ä¿¡ç®±
    -0.07
    宿
    -0.07
    ridge
    -0.07
    /www
    -0.06
    ligh
    -0.06
    YPD
    -0.06
    åĽ¾æĸ¯
    -0.06
    POSITIVE LOGITS
    astre
    0.07
    ç¾Ĭæ¯Ľ
    0.07
    nyder
    0.07
    åĨħ侧
    0.07
    æķ£
    0.07
     Dzi
    0.07
    è¾¾æĸ¯
    0.07
    ä½ĵåĨħçļĦ
    0.06
    à¸ķัà¹īà¸ĩ
    0.06
    inten
    0.06
    Activations Density 0.000%

    No Known Activations