© 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. 37861
    Prev
    Next
    INDEX
    Explanations

    petitioner vs respondent

    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
    æĪĸèĢħ缴æİ¥
    -0.08
    æĪĸ缴æİ¥
    -0.07
    æĪĸä¸İ
    -0.07
    —or
    -0.06
    oppel
    -0.06
    æĪIJç«ł
    -0.06
    éĶ»
    -0.06
    éĻ¢æł¡çļĦ
    -0.06
     Bef
    -0.06
    èĻ½çĦ¶ä¸įæĺ¯
    -0.06
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.11
     sedangkan
    0.11
    èĢĮ
    0.11
    èĢĮ以
    0.10
    èĢĮä½ł
    0.10
    èĢĮæĪij们
    0.10
    èĢĮåħ¶ä»ĸ
    0.09
     whereas
    0.09
    èĢĮ对
    0.09
    èĢĮ她
    0.09
    Activations Density 0.158%

    No Known Activations