© 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. 21155
    Prev
    Next
    INDEX
    Explanations

    appeal from orders or judgments

    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
    åı¸æ³ķé£İéĻ©
    -0.07
    é£
    -0.07
    æĭħä¿Ŀé£İéĻ©
    -0.06
    æĸ½æķij
    -0.06
    綱
    -0.06
    æ³ķéĻ¢åħ¬åijĬ
    -0.06
    åĪ°æŶ
    -0.06
    æİĪæĿĥèĮĥåĽ´åĨħ使çĶ¨
    -0.05
     bran
    -0.05
    ุà¸Ļ
    -0.05
    POSITIVE LOGITS
    ä¸įåIJĪçIJĨ
    0.11
     unjust
    0.10
    åģļåĩºçļĦ
    0.09
    ä¸įå½ĵ
    0.09
    ä¸įæľį
    0.09
     challenged
    0.09
    ä¸įåħ¬
    0.09
    ä¸įåħ¬å¹³
    0.09
     decisions
    0.09
    æľīå¼Ĥè®®
    0.09
    Activations Density 0.259%

    No Known Activations