© 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. 18564
    Prev
    Next
    INDEX
    Explanations

    cumulative sum and percent

    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
    ç¾İä¸Ń
    -0.07
    ictures
    -0.07
     lưỡng
    -0.07
    æ¯Ķä¾ĭ为
    -0.07
    é¦ĻæĸĻ
    -0.06
    åį¡è·¯
    -0.06
    estream
    -0.06
    æ°´ä¸ŃçļĦ
    -0.06
    çĴĢ
    -0.06
    izedName
    -0.06
    POSITIVE LOGITS
    .easing
    0.07
    åIJijéĺ³
    0.07
    ockey
    0.07
     Toro
    0.07
    ç´łåħ»
    0.07
     sweep
    0.07
    ichten
    0.07
     sigmoid
    0.06
    cita
    0.06
    èIJ¨æĸ¯
    0.06
    Activations Density 0.004%

    No Known Activations