© 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. 14732
    Prev
    Next
    INDEX
    Explanations

    formation, ballet, cross-country, pistol, volleyball, Cowboys

    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
    大å±ķ
    -0.08
    ẻ
    -0.08
    æħ·
    -0.07
    è¸ıè¸ıå®ŀ
    -0.07
    obot
    -0.07
     Propel
    -0.07
    æĸ°æŃĮ
    -0.07
    rea
    -0.07
    æĹłå¼Ĥè®®
    -0.07
    illi
    -0.07
    POSITIVE LOGITS
    ä¾ĽåºĶ产åĵģ
    0.07
    çĻ¾åĪĨçĻ¾
    0.06
     "\""
    0.06
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½åĪijæ³ķ
    0.06
    å®īåħ¨æĬĢæľ¯
    0.06
    it
    0.06
    asa
    0.06
     ìĿ´ìķ¼ê¸°
    0.06
    _RECE
    0.06
     fom
    0.06
    Activations Density 0.118%

    No Known Activations