© 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. 21977
    Prev
    Next
    INDEX
    Explanations

    http://

    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
    оÑĩ
    -0.08
    åIJĮ为
    -0.07
    ÃŃte
    -0.07
    ä¸İæīĢè¿°
    -0.07
    nable
    -0.07
    TURE
    -0.07
    ä¸ĵ家æĮĩåĩº
    -0.07
    ä¸ºæľ¬
    -0.06
    -end
    -0.06
    åijĺçļĦ
    -0.06
    POSITIVE LOGITS
    logan
    0.08
    toral
    0.08
    åı¯æ¢¦
    0.07
    æĿ¡ä»¶æĺ¯
    0.07
    缮æłĩæĺ¯
    0.07
    åıĪä½ķ
    0.06
    éĨļ
    0.06
    iels
    0.06
    ä¸ĢåĪ»
    0.06
    ä½ıæ°ij
    0.06
    Activations Density 0.006%

    No Known Activations