© 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. 64353
    Prev
    Next
    INDEX
    Explanations

    end of

    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
    ä¹ĭæ¯į
    -0.08
    åľ¨è¿Ļ次
    -0.08
    åľ¨å·¥ä½ľä¸Ĭ
    -0.08
    å°ĨæĿ¥çļĦ
    -0.08
    åŃ¦ä¹łä¸Ĭ
    -0.07
    à¸Ńà¸Ķีà¸ķ
    -0.07
    .abort
    -0.07
    åĩºè¡ĮçļĦ
    -0.07
    chg
    -0.07
     clé
    -0.07
    POSITIVE LOGITS
    å¸ļ
    0.07
     ÙĪبعد
    0.07
    漫éķ¿çļĦ
    0.07
    åĨ¤æŀī
    0.07
    igar
    0.07
     tenure
    0.07
     ÑģÑĢока
    0.07
     guise
    0.07
    è¿Ļ个è¿ĩç¨ĭ
    0.06
    estro
    0.06
    Activations Density 0.246%

    No Known Activations