© 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. 58371
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by math operations

    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
    gó
    -0.08
     chè
    -0.07
    ide
    -0.07
    omos
    -0.07
    aré
    -0.07
    upu
    -0.07
    表éĿ¢çļĦ
    -0.07
    ajn
    -0.07
    æĸĩå±±
    -0.07
    åįģå¹´
    -0.07
    POSITIVE LOGITS
    aign
    0.07
    aksa
    0.07
    èŀįä¼ļ
    0.06
    ä¸įæĸŃåĬłå¤§
    0.06
    çºł
    0.06
    æĪijçļĦ家乡
    0.06
     Downing
    0.06
    sons
    0.06
    utton
    0.06
    inja
    0.06
    Activations Density 0.068%

    No Known Activations