© 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. 25003
    Prev
    Next
    INDEX
    Explanations

    android, java, room, string utilities

    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
    дÑĮ
    -0.06
    ä¸ĬäºĨä¸Ģ
    -0.06
    人æĦı
    -0.06
    teres
    -0.06
    illon
    -0.06
    ters
    -0.06
    ä¸į欲
    -0.06
    жÑĮ
    -0.06
    ulli
    -0.06
    teri
    -0.06
    POSITIVE LOGITS
    âĵĴ
    0.08
    सà¥įथा
    0.07
    aval
    0.07
    建åįİ
    0.07
    rit
    0.07
     upstairs
    0.07
    ennen
    0.07
    apu
    0.07
    åIJ«éĩij
    0.07
    rome
    0.07
    Activations Density 1.017%

    No Known Activations