© 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. 24843
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code constructs

    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
    é¢Ĩ导çıŃåŃIJæĪIJåijĺ
    -0.06
    æĺ¯ä¸Ģ家以
    -0.06
     Bene
    -0.06
    ç§ijæĬĢåŀĭ
    -0.06
    è¿ĺåĸľæ¬¢
    -0.06
    esis
    -0.06
    çĤ¹ä¸ªèµŀ
    -0.06
    ë
    -0.06
    rip
    -0.06
    jo
    -0.06
    POSITIVE LOGITS
    ä¹ĺé£İ
    0.08
    æĹ¥æĹ¥
    0.08
    ạn
    0.07
    åıªå·®
    0.07
    æľĿå¤ķ
    0.07
    ARIO
    0.07
    ntag
    0.07
    alaus
    0.07
    æĸĩåĮĸéĥ¨
    0.07
    į¼
    0.07
    Activations Density 0.004%

    No Known Activations