© 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. 51236
    Prev
    Next
    INDEX
    Explanations

    code delimiters or structure

    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
    áles
    -0.08
    ibri
    -0.07
    åģļçļĦå°±æĺ¯
    -0.07
    lesi
    -0.07
    è¿Ļæł·çļĦæĥħåĨµ
    -0.07
    åı¯æĢķçļĦæĺ¯
    -0.07
    ivio
    -0.07
    è¡ĮåĬ¨èµ·æĿ¥
    -0.07
    å¾ĹéĿŀ常
    -0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.07
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.10
     here
    0.07
    arren
    0.07
    è¿ĻéĩĮæĺ¯
    0.06
    æ°¸å·ŀ
    0.06
     btw
    0.06
    ä¹Łè¡¨ç¤º
    0.06
    åľ¨è¿ĻéĩĮ
    0.06
    æľ¬æĸĩä¸Ń
    0.06
     Taken
    0.06
    Activations Density 0.046%

    No Known Activations