© 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. 47585
    Prev
    Next
    INDEX
    Explanations

    offender registration and parole

    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
    å¤ĸåķĨ
    -0.06
    篡
    -0.06
    åıįåŀĦæĸŃ
    -0.06
    è¡¥æ°Ķ
    -0.06
    åIJµæŀ¶
    -0.06
    åIJĪåIJĮæŶ
    -0.06
    ä¸ŃåĽ½å¸Ĥåľº
    -0.06
     overhead
    -0.06
     compr
    -0.06
    è·¨åĽ½åħ¬åı¸
    -0.06
    POSITIVE LOGITS
    ä¸İ社ä¼ļ
    0.11
     crimin
    0.11
    åĪijæľŁ
    0.11
     rehabilit
    0.10
     Criminal
    0.10
    åĴĮ社ä¼ļ
    0.10
    æĺ¯ç¤¾ä¼ļ
    0.10
    社ä¼ļ
    0.10
     society
    0.10
    criminal
    0.10
    Activations Density 0.145%

    No Known Activations