© 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. 58224
    Prev
    Next
    INDEX
    Explanations

    job titles and descriptions

    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
     trivial
    -0.06
    ä¸į欲
    -0.06
    éĨ
    -0.06
    åĽ
    -0.06
    æ¯ıæĪ·
    -0.06
    ç»ıåķĨ
    -0.06
    æĪª
    -0.06
     Vig
    -0.06
    ä¸įåĢ¼å¾Ĺ
    -0.06
    å¾®ä¸į足éģĵ
    -0.06
    POSITIVE LOGITS
    主è¦ģä»İäºĭ
    0.11
    çļĦå·¥ä½ľçݯå¢ĥ
    0.10
     responsibilities
    0.09
     salary
    0.09
     specializing
    0.09
    Salary
    0.09
     salaries
    0.09
    ä»ĸ们éľĢè¦ģ
    0.09
    ä»İäºĭ
    0.09
     roles
    0.09
    Activations Density 0.197%

    No Known Activations