© 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. 55426
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    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
    лада
    -0.07
    rops
    -0.07
    æĸ¹çļĦ
    -0.07
    íĴĢ
    -0.07
    aby
    -0.07
    æĹ¶èµ·
    -0.07
    riet
    -0.06
    èĶ¼
    -0.06
     '/')
    -0.06
    .names
    -0.06
    POSITIVE LOGITS
    åįĬæŃ¥
    0.07
    embre
    0.07
    交æīĢ
    0.07
    wein
    0.07
    ,private
    0.07
    æ´»æĢ§åĮĸ
    0.07
    ä½Ļ
    0.06
    enment
    0.06
    euw
    0.06
    顾åIJįæĢĿ
    0.06
    Activations Density 0.001%

    No Known Activations