© 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. 23045
    Prev
    Next
    INDEX
    Explanations

    Malaysia, Cashbox, group B, Khayyam, chrome, Tomcat

    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
    ering
    -0.07
    ç§į
    -0.07
    主è¦ģæĺ¯æĮĩ
    -0.07
    éģŃ
    -0.07
     ogl
    -0.07
    迹
    -0.06
    ä¸įåħħåĪĨ
    -0.06
    ered
    -0.06
    æĿ¾æĩĪ
    -0.06
    ä¸įèĥ½å®Įåħ¨
    -0.06
    POSITIVE LOGITS
     meticulous
    0.09
     meticulously
    0.08
     explicitly
    0.07
    ä¸įä»ħèĥ½
    0.07
    nud
    0.07
    åĸĦçĶ¨
    0.07
     explicit
    0.07
    æĺİç¡®
    0.07
    hq
    0.07
    utex
    0.07
    Activations Density 0.006%

    No Known Activations