© 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. 9658
    Prev
    Next
    INDEX
    Explanations

    from followed by date or location

    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
    åĴĮ
    -0.09
    ä¸Ģ个
    -0.09
    æĪij
    -0.08
    ä¸Ń
    -0.08
    天åı°
    -0.08
    ette
    -0.07
    ë¡ľ
    -0.07
    ä¸į详
    -0.07
    ectomy
    -0.07
    on
    -0.06
    POSITIVE LOGITS
    å§ĭèĩ³ç»Ī
    0.11
    å®ŀéĻħåĩºåıij
    0.11
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.10
    æĹ¥å¼Ģå§ĭ
    0.10
    æºIJ头ä¸Ĭ
    0.10
    ä¸įåIJĮè§Ĵ度
    0.09
    é«ĺåĪĨåĪ°ä½İåĪĨ
    0.09
    ä¸Ģéĸĭå§ĭ
    0.09
    å¹´å¼Ģå§ĭ
    0.09
    å¿ĥåºķ
    0.08
    Activations Density 0.001%

    No Known Activations