© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62990
    Prev
    Next
    INDEX
    Explanations

    public administration

    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
    ↵
    -0.08
    ation
    -0.07
    ivalent
    -0.07
    %H
    -0.07
    \t
    -0.07
    gether
    -0.06
     ê·¸ëŁ¬ë©´ìĦľ
    -0.06
        ↵
    -0.06
    pping
    -0.06
    [color
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.13
    ãĤ£
    0.12
    æĤ¨åı¯èĥ½
    0.10
    avanaugh
    0.10
    ãĤ¡
    0.09
    ами
    0.08
    entifier
    0.08
    ãĤ©
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    足çIJĥ俱ä¹IJéĥ¨
    0.07
    Activations Density 0.013%

    No Known Activations