© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    java.io, class, The Field

    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
     Pant
    -0.07
    ias
    -0.07
     sal
    -0.07
    ätzen
    -0.07
    é¢ľèī²
    -0.07
     perv
    -0.06
    ovel
    -0.06
    ignon
    -0.06
     pró
    -0.06
    ç¯ĩäºĮ
    -0.06
    POSITIVE LOGITS
    注æĦıçļĦæĺ¯
    0.07
     lupa
    0.07
    çļĦè¯Ħä»·æĺ¯
    0.07
    mpp
    0.07
    scoped
    0.07
    uddy
    0.06
    以身
    0.06
    æĿ¥ä¸´
    0.06
    ä¸ĭåįķ
    0.06
     Vieira
    0.06
    Activations Density 0.002%

    No Known Activations