© 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. 60556
    Prev
    Next
    INDEX
    Explanations

    json keys

    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
    å·ŀç«ĭ
    -0.07
    tart
    -0.07
    ovich
    -0.07
    itar
    -0.07
    çļĦ女
    -0.07
     Westbrook
    -0.07
    ãģĵãģª
    -0.07
    wich
    -0.07
    راط
    -0.07
    eka
    -0.07
    POSITIVE LOGITS
    æ¨
    0.08
    å¹³è¡Į
    0.06
    A
    0.06
    ffa
    0.06
     sounded
    0.06
     hab
    0.06
    常
    0.06
    人类
    0.06
    rush
    0.06
    elmet
    0.06
    Activations Density 0.011%

    No Known Activations