© 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. 46084
    Prev
    Next
    INDEX
    Explanations

    Chinese court sentences

    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
    ä¾Ŀ
    -0.07
    æľĢ
    -0.07
    ä¸ŃçļĦæīĢæľī
    -0.07
    æľī太å¤ļ
    -0.06
    è¡·å¿ĥ
    -0.06
    åIJĮçIJĨ
    -0.06
    çļĦæīĢæľī
    -0.06
    åIJĦåĽ½
    -0.06
    åIJĮæł·
    -0.06
    ä¸įåıĬ
    -0.06
    POSITIVE LOGITS
    好åĥıæĺ¯
    0.13
     reportedly
    0.11
    æį®è¯´
    0.10
    çļĦä¸ĢäºĽ
    0.09
    åı¯èĥ½å°±æĺ¯
    0.09
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    0.09
    ä¸ĢäºĽéĹ®é¢ĺ
    0.09
     údaj
    0.09
    æĺ¯æ¯Ķè¾ĥ
    0.09
     ÑıкобÑĭ
    0.08
    Activations Density 0.034%

    No Known Activations