© 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. 24498
    Prev
    Next
    INDEX
    Explanations

    pattern

    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
    ...
    -0.07
    éģ¨
    -0.06
    ãĢĤwww
    -0.06
    ale
    -0.06
    าà¸Ļัà¹īà¸Ļ
    -0.06
    arin
    -0.06
    tt
    -0.06
     afterwards
    -0.06
    èij
    -0.06
    ettle
    -0.05
    POSITIVE LOGITS
    éĢļè¿ĩ以ä¸Ĭ
    0.10
     tehát
    0.09
    ankind
    0.09
    venes
    0.08
    ä¸įåı¯æĢķ
    0.08
    adura
    0.08
    è¿ŀåIJĮ
    0.08
    ITS
    0.08
    .substr
    0.07
    è¿Ļæł·ä¸Ģç§į
    0.07
    Activations Density 0.001%

    No Known Activations