© 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. 29759
    Prev
    Next
    INDEX
    Explanations

    usage

    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
    æīĭå¿Ļ
    -0.07
     orchestr
    -0.07
    æĸ°æµª
    -0.07
     Timing
    -0.06
    æĵįä½ľæµģç¨ĭ
    -0.06
    .Timer
    -0.06
    Dispatcher
    -0.06
    æī§è¡Įç¨ĭåºı
    -0.06
    çľ
    -0.06
    åĴĮæĵįä½ľ
    -0.06
    POSITIVE LOGITS
    Naming
    0.09
     prist
    0.08
     naming
    0.08
    éĿĻæĢģ
    0.08
     Naming
    0.08
    åŃĺåĤ¨
    0.08
    åĤ¨åŃĺ
    0.08
    repos
    0.07
    åij½åIJįçļĦ
    0.07
    æłĸ
    0.07
    Activations Density 0.956%

    No Known Activations