© 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. 55627
    Prev
    Next
    INDEX
    Explanations

    question or explanation

    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
     ÐļÑĢаÑģи
    -0.08
    ä¸ĭåIJĮ
    -0.07
    ä¸īéĩĮ
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    addir
    -0.07
     nhau
    -0.07
     ÐŁÑĢедÑģÑĤави
    -0.07
    è®ĵæĤ¨
    -0.07
    赶紧æĿ¥
    -0.07
    itmap
    -0.07
    POSITIVE LOGITS
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.09
    è¦ģ注æĦıçļĦæĺ¯
    0.08
    尤为
    0.08
    åĢ¼å¾Ĺ注æĦıçļĦæĺ¯
    0.08
    èĢĮéĢłæĪIJ
    0.08
     furthermore
    0.07
    缸æ¯Ķä¹ĭä¸ĭ
    0.07
    æѤå¤ĸ
    0.07
    æį¢è¨Ģä¹ĭ
    0.07
     However
    0.07
    Activations Density 0.401%

    No Known Activations