© 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. 51499
    Prev
    Next
    INDEX
    Explanations

    Wen Zhang

    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
    ../../../
    -0.09
    ../../
    -0.09
    ../../../../
    -0.07
    ftware
    -0.07
    онов
    -0.07
    ÑĢанже
    -0.07
    zelfde
    -0.07
    ัà¸Ļà¸ĺà¹Į
    -0.07
    udios
    -0.06
    pital
    -0.06
    POSITIVE LOGITS
    edly
    0.10
    ative
    0.10
    å¸ĿçļĦ
    0.09
     xuôi
    0.08
    istry
    0.08
    UYÃĬN
    0.08
    aceous
    0.08
    ilh
    0.08
    icen
    0.08
    ág
    0.08
    Activations Density 0.003%

    No Known Activations