© 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. 62643
    Prev
    Next
    INDEX
    Explanations

    Black Knight, Mild, Ya-Ya, Cake

    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
    红åı¶
    -0.07
    ä¸ĢæĭĽ
    -0.06
    uning
    -0.06
    伸
    -0.06
    åħ¼æĢ»ç»ıçIJĨ
    -0.06
    çļĦå¸Ĥæ°ij
    -0.06
    _axes
    -0.06
    /comment
    -0.06
    ypi
    -0.06
    umont
    -0.06
    POSITIVE LOGITS
    è¿Ļ个åIJįåŃĹ
    0.11
    ä¸įæĺ¯ä¸Ģ个
    0.11
    ä½ľä¸ºä¸Ģç§į
    0.10
     refers
    0.09
    æ³ĽæĮĩ
    0.09
    —an
    0.09
    æĮĩçļĦæĺ¯
    0.09
    è¿Ļ个åĵģçīĮ
    0.09
    —a
    0.09
    ä½ľä¸ºä¸Ģ个
    0.09
    Activations Density 0.146%

    No Known Activations