© 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. 16435
    Prev
    Next
    INDEX
    Explanations

    respondent, petitions, appeals, mother

    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
    æĬķèµĦæĪĸ
    -0.08
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.08
    èĭ¥
    -0.08
    èĭ¥æĺ¯
    -0.08
    强éĻ©
    -0.08
    prese
    -0.08
    ighted
    -0.07
    æĪĸæĺ¯
    -0.07
    æĪĸå°ı
    -0.07
    å¼ĢåºŃåħ¬åijĬ
    -0.07
    POSITIVE LOGITS
     allegedly
    0.11
     purported
    0.10
     alleged
    0.10
     defendants
    0.08
    对åİŁåijĬ
    0.08
    ä¸İ被åijĬ
    0.08
     testified
    0.08
     defendant
    0.08
     lacked
    0.08
     plaintiffs
    0.08
    Activations Density 0.932%

    No Known Activations