© 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. 18149
    Prev
    Next
    INDEX
    Explanations

    programming or technical instructions

    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
    æĦıæĢĿ
    -0.07
     fur
    -0.07
    .Marshal
    -0.06
    apati
    -0.06
     Roe
    -0.06
    ковÑĭ
    -0.06
    çļĦæĦıæĢĿ
    -0.06
    enth
    -0.06
    æ´Ľä¼Ĭ
    -0.06
    ä¸įå¤ļ说
    -0.06
    POSITIVE LOGITS
    åıªèĥ½åľ¨
    0.19
    åıªæľīåľ¨
    0.17
    çļĦåīįæıIJ
    0.16
    åīįæıIJæĺ¯
    0.16
    åıªå¯¹
    0.14
     Requires
    0.14
    åıªåľ¨
    0.14
    Requires
    0.14
     requires
    0.13
    ä¾Ŀèµĸäºİ
    0.13
    Activations Density 0.249%

    No Known Activations