© 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. 63331
    Prev
    Next
    INDEX
    Explanations

    -mediated, -induced, -dependent, -based mechanisms

    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
    åĴĮå¿«ä¹IJ
    -0.08
    åļ¼
    -0.06
    åĴĮçĶŁäº§
    -0.06
    åĴĮ幸ç¦ı
    -0.06
    åĴĮ责任
    -0.06
    åĴĮå®īåħ¨
    -0.06
     humiliating
    -0.06
     darn
    -0.06
    andum
    -0.06
     Pio
    -0.06
    POSITIVE LOGITS
    èµ·çļĦ
    0.10
    æĪIJçļĦ
    0.10
    uced
    0.09
     ìĿ¸íķľ
    0.09
    æŃ¤èµ·
    0.09
    èĢĮæĪIJçļĦ
    0.09
    resher
    0.08
    bies
    0.08
    éģĵè¿ľ
    0.08
    èĢĮæĿ¥çļĦ
    0.08
    Activations Density 0.123%

    No Known Activations