© 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. 64885
    Prev
    Next
    INDEX
    Explanations

    superior performance or features

    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
    ondag
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.09
    à¸Ļà¸Ńà¸ĩ
    -0.09
    bruch
    -0.08
    otron
    -0.08
    æ°ı
    -0.08
    away
    -0.08
    iban
    -0.08
    ä¸ĵèIJ¥åºĹ
    -0.08
    athon
    -0.08
    POSITIVE LOGITS
    åĬ£
    0.08
    æĺĻ
    0.07
    -looking
    0.07
    纷åijĪ
    0.07
    åĴĮä¸į足
    0.07
    à¹Ģลิศ
    0.07
     hẳn
    0.07
    åľ°ä½į
    0.07
    æĹłæ¯ĶçļĦ
    0.07
    ä»·å»ī
    0.07
    Activations Density 0.023%

    No Known Activations