© 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. 56050
    Prev
    Next
    INDEX
    Explanations

    criminal proceedings and legal matters

    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
    离岸
    -0.07
     cheats
    -0.06
    å©Ĩ
    -0.06
    ä¸ĩåįĥ
    -0.06
    alous
    -0.06
    æĺł
    -0.06
     cheated
    -0.06
    æ°ijäºĭè¡Į为èĥ½åĬĽ
    -0.06
    che
    -0.06
     cheat
    -0.06
    POSITIVE LOGITS
     Criminal
    0.10
    åĪijäºĭè¯ī讼
    0.10
    åĪijäºĭæ¡Ī件
    0.10
    移éĢģ
    0.10
    ä¾¦æŁ¥
    0.10
     criminal
    0.10
    ç¾ģæĬ¼
    0.09
    onia
    0.09
    çĬ¯ç½ª
    0.09
    çĬ¯ç½ªå«Įçĸij人
    0.09
    Activations Density 0.113%

    No Known Activations