© 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. 19359
    Prev
    Next
    INDEX
    Explanations

    programming keywords: if, uint, var, return

    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
    该è¡Į
    -0.08
    ÙħÛĮÙĨ
    -0.08
    è¾¹éĻħ
    -0.08
    个人è¡Į为
    -0.07
    rine
    -0.07
    ÙħÙĬÙĨ
    -0.07
    usize
    -0.07
     usize
    -0.07
    ubre
    -0.06
    åħ¶æ¬¡
    -0.06
    POSITIVE LOGITS
    cez
    0.07
    asuk
    0.07
    ikk
    0.07
    è·Łä»ĸ
    0.07
    iskey
    0.07
    çĻ½æĹ¥
    0.06
    RIPT
    0.06
    è·Łä½ł
    0.06
    arren
    0.06
    é§Ĵ
    0.06
    Activations Density 0.038%

    No Known Activations