© 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. 55770
    Prev
    Next
    INDEX
    Explanations

    job duties and tasks

    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
    ç»ıæµİå®ŀåĬĽ
    -0.07
    é¦ĸ家
    -0.07
     rav
    -0.07
    å·¨èµĦ
    -0.07
     outlaw
    -0.06
    éĨĴæĤŁ
    -0.06
     Paz
    -0.06
    两岸
    -0.06
    å®ļå±ħ
    -0.06
     millions
    -0.06
    POSITIVE LOGITS
    åĴĮåIJĮäºĭ
    0.13
    å¯¹å·¥ä½ľ
    0.13
    åľ¨å·¥ä½ľä¸Ń
    0.12
    æĬĬå·¥ä½ľ
    0.12
    å§Ķæ´¾
    0.11
    å·¥ä½ľä»»åĬ¡
    0.11
     workload
    0.11
    ä»»åĬ¡çļĦ
    0.11
     ìĹħ무
    0.11
    å²Ĺä½į
    0.11
    Activations Density 0.150%

    No Known Activations