© 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. 50903
    Prev
    Next
    INDEX
    Explanations

    code formatting indicators

    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
    æĻ°
    -0.06
    /
    -0.06
    -&
    -0.06
    ime
    -0.06
    山人
    -0.06
     stuff
    -0.06
    åľ°æĬĬ
    -0.06
    ')</
    -0.06
    Assertions
    -0.06
    agnes
    -0.06
    POSITIVE LOGITS
    æľĢæĸ°ç«łèĬĤ
    0.07
    åIJĮä¸Ĭ
    0.07
    åIJĮåľ¨
    0.07
    ioca
    0.07
     spos
    0.07
    ÉĻrÉĻ
    0.07
    dued
    0.07
    itel
    0.07
    æ·¡èĸĦ
    0.07
    ileo
    0.07
    Activations Density 0.035%

    No Known Activations