© 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. 42728
    Prev
    Next
    INDEX
    Explanations

    title, name, class, package

    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
    .currentTarget
    -0.08
    UrlParser
    -0.07
    ¦
    -0.07
    igate
    -0.07
    ä¸Ĭä¼łèĢħ
    -0.07
    odob
    -0.07
    åŃ£çļĦ
    -0.07
     scad
    -0.07
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    -0.07
    ställ
    -0.07
    POSITIVE LOGITS
    çģ«åĬĽ
    0.07
    ï½ŀãĢĤ
    0.07
    lÄħ
    0.07
     filetype
    0.06
     Kus
    0.06
    èĩ³å°ij
    0.06
    濯
    0.06
    èĪĴ
    0.06
     Sard
    0.06
    zil
    0.06
    Activations Density 0.003%

    No Known Activations