© 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. 41664
    Prev
    Next
    INDEX
    Explanations

    static site, private repo, binary image

    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
     Found
    -0.07
    Found
    -0.07
    _found
    -0.06
     (
    -0.06
    åŃĺ
    -0.06
    -0.06
    çļĦå¾®ç¬ij
    -0.06
    CLK
    -0.06
    found
    -0.06
     -
    -0.05
    POSITIVE LOGITS
    ifie
    0.10
     bersangkutan
    0.08
    ãģªãĤīãģ§ãģ¯
    0.08
     LATIN
    0.08
    ä½ĵçİ°åľ¨
    0.08
    rocess
    0.08
    ÙĴÙĦÙIJ
    0.08
    ç½ijé¦ĸ页
    0.08
    ãģªãĤīãģ§ãģ¯ãģ®
    0.08
    rive
    0.08
    Activations Density 0.217%

    No Known Activations