© 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. 24691
    Prev
    Next
    INDEX
    Explanations

    case numbers with JV or DR

    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
    arty
    -0.07
    omer
    -0.07
    æĺ¯ä¸Ģ个éĿŀ常
    -0.06
    æĪĸèĢħåħ¶ä»ĸ
    -0.06
    ä»İ严治åħļ
    -0.06
     ê´Ģ볨íķĺìŬ
    -0.06
    .Dir
    -0.06
    pos
    -0.06
    ÅĤam
    -0.06
    iesen
    -0.06
    POSITIVE LOGITS
     appunto
    0.07
    ilea
    0.07
    ichte
    0.07
    clu
    0.07
    apar
    0.07
    ä¹ĭåıĪ
    0.07
     enten
    0.06
    ê»ı
    0.06
    ;*
    0.06
    GetMethod
    0.06
    Activations Density 0.572%

    No Known Activations