© 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. 25879
    Prev
    Next
    INDEX
    Explanations

    Surprise, Transart, The, More, For, Both, Children

    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
    ìĿĺ
    -0.11
    ãģ®
    -0.10
    çļĦåIJĦç§į
    -0.09
    çļĦ责任
    -0.09
    çļĦæĥħåĨµä¸ĭ
    -0.09
    çļĦå¤ļ
    -0.09
    çļĦ两
    -0.09
    (\
    -0.09
    çļĦè¿ĩç¨ĭä¸Ń
    -0.08
    çļĦé£İéĻ©
    -0.08
    POSITIVE LOGITS
    Âł
    0.13
    ³³³
    0.13
    ³³
    0.13
    ÛĮ
    0.12
    ³³³³³³³
    0.12
    nya
    0.11
    ³³³³
    0.11
     Âł
    0.11
    ³³³³³³³³
    0.10
    ÑģÑı
    0.10
    Activations Density 1.806%

    No Known Activations