© 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. 20107
    Prev
    Next
    INDEX
    Explanations

    test or run

    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
     synerg
    -0.08
    è¢«ä½ł
    -0.07
    ainter
    -0.07
    Expiration
    -0.07
    éĺIJ
    -0.07
    æĿ¥æİ¥
    -0.07
    éĺIJæĺİ
    -0.07
    ä¸įè¿ĩæĿ¥
    -0.07
     surface
    -0.06
    å·¥ä½ľå²Ĺä½į
    -0.06
    POSITIVE LOGITS
     thá»Ń
    0.08
    åĨįçı¾
    0.08
    fø
    0.07
    åłĤçļĦ
    0.07
    åłĤ
    0.07
    zÄħt
    0.07
    åĽŃçļĦ
    0.07
    ç¾½
    0.07
    warts
    0.07
    å°±ä¼ļåıijçİ°
    0.06
    Activations Density 0.034%

    No Known Activations