© 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. 65103
    Prev
    Next
    INDEX
    Explanations

    code comments and special characters

    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
    åĬłè½½æĽ´å¤ļ
    -0.08
    éĺħè¯»æľ¬æĸĩ
    -0.08
    ház
    -0.08
    /rem
    -0.08
    æıIJè¦ģ
    -0.08
    apä
    -0.08
    ä¸įèĭŁ
    -0.08
    hia
    -0.08
    thu
    -0.07
    åĴĮ社ä¼ļåıijå±ķ
    -0.07
    POSITIVE LOGITS
    浪漫çļĦ
    0.07
    ical
    0.07
    inux
    0.06
    ä¾į
    0.06
    ically
    0.06
    frican
    0.06
     prelimin
    0.06
    fty
    0.06
    æĬ¤æ³ķ
    0.06
     ÙħÙĨا
    0.06
    Activations Density 0.080%

    No Known Activations