© 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. 47985
    Prev
    Next
    INDEX
    Explanations

    accounting officer

    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
    igh
    -0.09
    ç»ıèIJ¥é¡¹çĽ®
    -0.08
    elves
    -0.08
    éģ¨
    -0.08
    edException
    -0.08
    ر
    -0.07
    edList
    -0.07
    ãģ¹ãģı
    -0.07
    ç§ijåѦä¸İå·¥ç¨ĭ
    -0.07
    æķĻèĤ²èĢĥè¯ķ
    -0.07
    POSITIVE LOGITS
    rypt
    0.08
    åĴĮæ³ķå¾ĭ
    0.07
    åĪºå®¢
    0.07
    greg
    0.07
    èģĮ称
    0.07
    ept
    0.07
    ÙĪÙĨØ©
    0.06
     traditionnelle
    0.06
    æĺ¯ä¸ĢéŨ
    0.06
    ±
    0.06
    Activations Density 0.001%

    No Known Activations