© 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. 47298
    Prev
    Next
    INDEX
    Explanations

    .ttf format or file names

    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
    merican
    -0.10
    ä¹ĭä¸Ģ
    -0.09
    olume
    -0.09
    ä¹ĭä¸Ģæĺ¯
    -0.09
    ä¹ĭåIJİ
    -0.09
    ä¹ĭè¾Ī
    -0.08
    ä¹ĭ说
    -0.08
    acific
    -0.08
    ä¹ĭé£İ
    -0.08
     Ñģобой
    -0.07
    POSITIVE LOGITS
    /--
    0.11
    åĭĩå¾Ģ缴åīį
    0.10
    ä¸įåı¯æĢĿè®®
    0.10
    身临åħ¶å¢ĥ
    0.10
    /+
    0.10
    èī²åĪĹ
    0.09
    æŀĿèĬ±
    0.09
    .herokuapp
    0.09
    celona
    0.09
    åIJĦç§įåIJĦæł·
    0.09
    Activations Density 0.960%

    No Known Activations