© 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. 46123
    Prev
    Next
    INDEX
    Explanations

    technique, training, lessons, study

    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
     economists
    -0.09
    æĻºåºĵ
    -0.08
     Polic
    -0.08
    æ°ijæĦı
    -0.08
     nominee
    -0.07
    æĸ°ç»ıæµİ
    -0.07
     Finance
    -0.07
    ç²¾æĺİ
    -0.07
    é«ĺæĸ°æĬĢæľ¯äº§ä¸ļ
    -0.07
     Industries
    -0.07
    POSITIVE LOGITS
    åŁºæľ¬åĬŁ
    0.12
     technique
    0.10
     mastering
    0.10
    åĪ»èĭ¦
    0.10
     beginner
    0.10
    ç»ĥä¹ł
    0.10
     Technique
    0.10
    æīĵå¥½åŁºç¡Ģ
    0.10
    æĬĢæ³ķ
    0.09
    åĪĿåѦèĢħ
    0.09
    Activations Density 0.326%

    No Known Activations