© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12044
    Prev
    Next
    INDEX
    Explanations

    into PDF

    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
    оÑģоб
    -0.06
    漪
    -0.06
    ÑģÑĭ
    -0.06
    åIJĽçİĭ
    -0.06
    çĮ¿
    -0.06
    vw
    -0.05
     Conan
    -0.05
    COS
    -0.05
    ujan
    -0.05
    ä½łçļĦæľĭåıĭ
    -0.05
    POSITIVE LOGITS
    maa
    0.08
    ikipedia
    0.07
    ViewById
    0.07
    Ñĥди
    0.07
     daqu
    0.07
    å°ıæıIJ示
    0.07
     handl
    0.07
    æľ¬å¸ĸ
    0.07
    rist
    0.07
    æľĢé«ĺ人æ°ijæ³ķéĻ¢åħ³äºİ审çIJĨ
    0.07
    Activations Density 0.471%

    No Known Activations