© 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. 57687
    Prev
    Next
    INDEX
    Explanations

    semicolon as separator

    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
    åĬłæĭ¿å¤§
    -0.08
    меÑĩа
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    çļĦéĢĶå¾Ħ
    -0.07
    orary
    -0.07
    åłĤåłĤ
    -0.07
    ivate
    -0.07
    ILER
    -0.07
    ixel
    -0.07
    ston
    -0.07
    POSITIVE LOGITS
    Õ¡Õ¾
    0.08
    ä¸Ģæĸij
    0.08
    attle
    0.08
    infra
    0.08
    åŁł
    0.07
    å´İ
    0.07
    Úº
    0.07
    ÙħÙĨت
    0.07
    lepÅ¡ÃŃ
    0.07
    otra
    0.07
    Activations Density 0.077%

    No Known Activations