© 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. 13133
    Prev
    Next
    INDEX
    Explanations

    legal opinions and dissenting statements

    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
    åĴĮç¾İ
    -0.08
    nero
    -0.07
    ongyang
    -0.07
    æ¯Ķ以åīį
    -0.07
    äºĭä¸ļåįķä½įåħ¬å¼ĢæĭĽèģĺ
    -0.07
    æį®ä»ĭç»į
    -0.07
    å±±åı£
    -0.07
    >Type
    -0.06
    PerPage
    -0.06
    peÄį
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.08
    keh
    0.06
    èĭ¦å¿ĥ
    0.06
    ween
    0.06
    sel
    0.06
    ãģ¾ãģĽãĤĵãģĭ
    0.06
    ao
    0.05
    æĬ½åĩº
    0.05
    еÑĩаÑĤ
    0.05
    na
    0.05
    Activations Density 0.320%

    No Known Activations