© 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. 11384
    Prev
    Next
    INDEX
    Explanations

    case against a Michigan student

    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
    产åĵģçī¹çĤ¹
    -0.08
    udou
    -0.08
    产åĵģç»ĵæŀĦ
    -0.08
    å°ĨæѤ
    -0.08
    å®ıåĽ¾
    -0.07
    æĬ¥åijĬ书
    -0.07
    edig
    -0.07
    åĬ©ä½ł
    -0.07
    人被
    -0.07
    æıIJéĨĴæĤ¨
    -0.07
    POSITIVE LOGITS
    åıĬ对
    0.11
    以åıĬ对
    0.10
    æĪĸ对
    0.09
    åĴĮ对
    0.09
    å°±æĺ¯å¯¹
    0.08
    çī¹åĪ«æĺ¯å¯¹
    0.08
    åĬłä»¥
    0.08
    æ¯Ķ对
    0.07
    çľĭåľ¨çľ¼éĩĮ
    0.07
    è¿Ľè¡ĮäºĨ
    0.07
    Activations Density 0.012%

    No Known Activations