© 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. 3667
    Prev
    Next
    INDEX
    Explanations

    misuse of funds or property

    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
    akest
    -0.08
    kev
    -0.08
    è·¤
    -0.08
    鸳
    -0.08
    åĭ¤äºİ
    -0.08
     ketat
    -0.07
    强度é«ĺ
    -0.07
     boycott
    -0.07
    ç«Ńè¯ļ
    -0.07
    HEST
    -0.07
    POSITIVE LOGITS
    æķ°é¢Ŀ
    0.08
    åıĺçİ°
    0.08
    ä¿Ŀ管
    0.07
    个人çļĦ
    0.07
     personal
    0.07
    éļIJç§ĺ
    0.07
    ä¸Ģ空
    0.07
    串
    0.07
     amounts
    0.07
     loot
    0.07
    Activations Density 0.014%

    No Known Activations