© 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. 1093
    Prev
    Next
    INDEX
    Explanations

    Ottoman and Austrian Empires

    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
    åįĹéŁĵ
    -0.09
    acce
    -0.08
    åľ¨åħ¨çľģ
    -0.08
    ipur
    -0.08
    ç¬ĭ
    -0.07
    æ´¼
    -0.07
     norway
    -0.07
    æ²³å¸Ĥ
    -0.07
    æ²³éķĩ
    -0.07
    èµģ
    -0.07
    POSITIVE LOGITS
    å¸ĿåĽ½
    0.10
     imperial
    0.10
    å¸ĿåĽ½çļĦ
    0.08
     Empire
    0.08
     empire
    0.08
     Imperial
    0.07
    æĹĹä¸ĭçļĦ
    0.07
    à¹Ģà¸ģร
    0.07
     Constantin
    0.07
    é¢ĨåľŁ
    0.07
    Activations Density 0.081%

    No Known Activations