© 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. 32597
    Prev
    Next
    INDEX
    Explanations

    code tag syntax like `<div`

    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
    毡
    -0.07
    æĥħç»ĵ
    -0.07
    ÙĪدة
    -0.07
    elden
    -0.07
    ãģĦãģª
    -0.07
    èĪį
    -0.07
    .Extension
    -0.07
    åºĶåIJij
    -0.07
    >(_
    -0.07
    çŁ¥å·±
    -0.06
    POSITIVE LOGITS
    ä¸ĢæľŁ
    0.08
    åĢĻ
    0.07
    orsi
    0.07
    urunkan
    0.07
    å¦Ĥæŀľä½łåľ¨
    0.07
    etes
    0.07
    ovsky
    0.06
     typically
    0.06
     growing
    0.06
     usually
    0.06
    Activations Density 0.006%

    No Known Activations