© 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. 48997
    Prev
    Next
    INDEX
    Explanations

    followed by a comma

    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
    ;if
    -0.07
    ;**
    -0.07
    ";
    -0.07
    *;
    -0.07
    ”;
    -0.07
    ãĢįãĢĮ
    -0.07
    .";
    -0.07
    çŁ¥éģĵåIJĹ
    -0.07
    );\
    -0.07
     rowspan
    -0.07
    POSITIVE LOGITS
    ,it
    0.13
     ÙģØ¥ÙĨ
    0.12
     ÙģØ¥ÙĨÙĩ
    0.12
     maka
    0.12
    ,is
    0.11
    çļĦè¯Ŀ
    0.11
    çļĦ話
    0.11
     thì
    0.11
    æĢİä¹ĪåĬŀ
    0.10
    该æĢİä¹ĪåĬŀ
    0.10
    Activations Density 1.099%

    No Known Activations