© 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. 60960
    Prev
    Next
    INDEX
    Explanations

    adults, males, language, complex, focal, dry

    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
    å±ķå¼Ģåħ¨æĸĩ
    -0.09
    æķĻèĤ²åѦéĻ¢
    -0.08
    å¾Ģå¤ĸ
    -0.08
    ÑĩиÑĤа
    -0.08
    _through
    -0.07
    astique
    -0.07
    æľĢæĸ°ç«łèĬĤ
    -0.07
    emus
    -0.07
    oug
    -0.07
    ebel
    -0.07
    POSITIVE LOGITS
    æĹłéĤª
    0.06
    yt
    0.06
    yi
    0.06
     ni
    0.06
    åĴĮéĿŀ
    0.06
    ä»ĺãģį
    0.06
    rav
    0.06
    iture
    0.06
    ified
    0.06
    ync
    0.06
    Activations Density 0.800%

    No Known Activations