© 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. 22193
    Prev
    Next
    INDEX
    Explanations

    United States, President 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
    æ°´æĺ¯
    -0.12
    åħīæĺ¯
    -0.11
    家æĺ¯
    -0.10
    åħ¬åı¸æĺ¯
    -0.10
    æķĻèĤ²æĺ¯
    -0.10
    ãĤ¹ãģ¯
    -0.10
    æ³ķæĺ¯
    -0.09
    人æĺ¯
    -0.09
    ç³»ç»Łæĺ¯
    -0.09
    ä»»åĬ¡æĺ¯
    -0.09
    POSITIVE LOGITS
    /{}/
    0.11
    æĿ¡ä»¶ä¸ĭçļĦ
    0.10
    >::
    0.10
    æĥħå½¢çļĦ
    0.09
    æĿ¡ä»¶ä¸ĭ
    0.09
    ãĤĤãģ®ãģ®
    0.09
    æŶæīĢ
    0.08
    /*/
    0.08
    åIJĦé¡¹å·¥ä½ľçļĦ
    0.08
    产ä¸ļåıijå±ķçļĦ
    0.08
    Activations Density 0.054%

    No Known Activations