© 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. 64368
    Prev
    Next
    INDEX
    Explanations

    icons and UI elements

    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
     rep
    -0.08
    å¿ħè¦ģ
    -0.07
    ä¸ĢæŶ
    -0.06
    åIJ¯
    -0.06
     dec
    -0.06
    å¾Ĺè¿ĩ
    -0.06
    ×Ĺ×Ļ×Ŀ
    -0.06
    িত
    -0.06
     sire
    -0.06
    æĺİçģ«
    -0.06
    POSITIVE LOGITS
    peq
    0.08
    æħ¾
    0.08
    ifr
    0.08
    gefü
    0.08
    pga
    0.08
    chmod
    0.08
    oga
    0.07
    fyl
    0.07
    建ä¸ļ
    0.07
    สรรà¸ŀ
    0.07
    Activations Density 0.014%

    No Known Activations