© 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. 16936
    Prev
    Next
    INDEX
    Explanations

    education and learning resources

    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
    çľĭæ¸ħæ¥ļ
    -0.07
    Tho
    -0.07
    mayı
    -0.07
    BAB
    -0.06
    æĸ°ä¹¦æݨèįIJ
    -0.06
    é¡·
    -0.06
    ×ĺ×Ļפ
    -0.06
    åŃ¦æ´¾
    -0.06
     accounted
    -0.06
     Academia
    -0.06
    POSITIVE LOGITS
    STE
    0.10
    å¯ĵæķĻäºİ
    0.09
    æ¿ĢåıijåѦçĶŁ
    0.09
    æ¿Ģåıij
    0.09
     engaging
    0.08
    让åŃ©åŃIJ们
    0.08
    让åѦçĶŁ
    0.08
     вов
    0.08
    é¼ĵåĬ±ä»ĸ们
    0.08
    让ä»ĸ们
    0.08
    Activations Density 0.229%

    No Known Activations