© 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. 56093
    Prev
    Next
    INDEX
    Explanations

    arterial systems and perforating anatomy

    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
    çIJĨæĢ§
    -0.07
    稳
    -0.07
    æĮª
    -0.07
     testing
    -0.07
    å¿Į
    -0.06
     rational
    -0.06
    cv
    -0.06
     Autof
    -0.06
    è¿«
    -0.06
    å°±æĺ¯æľĢ好çļĦ
    -0.06
    POSITIVE LOGITS
    åĪĨåĩº
    0.09
    æ±ĩåħ¥
    0.09
    å¾ĹåIJį
    0.08
    èµ°è¡Į
    0.08
    åIJĮåIJį
    0.08
    ä¾ĭå¤ĸ
    0.07
     ÑĤопо
    0.07
     اÙĦتشرÙĬ
    0.07
    .thread
    0.07
    à¸ģà¸ģ
    0.07
    Activations Density 0.067%

    No Known Activations