© 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. 32503
    Prev
    Next
    INDEX
    Explanations

    lists with "and" and numbers

    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
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.09
    è¿Ļ两ä½į
    -0.09
    éĤ£ä¸¤ä¸ª
    -0.09
    è¿Ļ两个
    -0.08
    è¿Ļ两款
    -0.08
     berdua
    -0.08
     обоиÑħ
    -0.08
     kedua
    -0.08
    æľĢç¾İçļĦ
    -0.08
     entrambe
    -0.08
    POSITIVE LOGITS
    ãģ©ãĤĮãĤĤ
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
    all
    0.07
    вÑģе
    0.07
    éĵ®
    0.07
     all
    0.07
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    0.07
    ç§įç§į
    0.06
     uniformly
    0.06
    éĴ§
    0.06
    Activations Density 0.007%

    No Known Activations