© 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. 13887
    Prev
    Next
    INDEX
    Explanations

    retail stores and shops

    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
    éħĴåºĹ管çIJĨ
    -0.09
    æijĩ篮
    -0.08
    æĻļå®´
    -0.08
    ãģ®ãĥĽãĥĨãĥ«
    -0.08
    åľ¨å·¥ä½ľä¸Ĭ
    -0.07
     pipelines
    -0.07
    éħĴæĿ¯
    -0.07
    è¨ĤæĪ¿
    -0.07
    书æĪ¿
    -0.07
    çłĶåıijåĽ¢éĺŁ
    -0.07
    POSITIVE LOGITS
    鼶åĶ®
    0.11
     retail
    0.10
     ais
    0.09
    ä¸ļæĢģ
    0.09
    ç»ıèIJ¥çļĦ
    0.09
    ÏĢÏī
    0.09
    cery
    0.09
    éĻĪåĪĹ
    0.09
    empor
    0.09
    å¼Ģä¸ļ
    0.08
    Activations Density 0.427%

    No Known Activations