© 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. 23716
    Prev
    Next
    INDEX
    Explanations

    names of places and organizations

    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
    ameni
    -0.08
     Blasio
    -0.08
    emers
    -0.07
    æľªå®ĮæĪIJ
    -0.07
     Boehner
    -0.07
     \`
    -0.07
    erma
    -0.07
    ertain
    -0.07
    onio
    -0.07
    ä»İ天
    -0.07
    POSITIVE LOGITS
    ä¸Ģ个åı«
    0.10
    ä¹ĭä¸ĢçļĦ
    0.10
    ì²´ìĿ¸
    0.10
    ìĤ¬ìĿ¸
    0.09
     bernama
    0.09
    ìŀIJìĿ¸
    0.08
    èijĹåIJį
    0.08
    人马
    0.08
    åIJį为
    0.08
     namens
    0.08
    Activations Density 1.196%

    No Known Activations