© 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. 15665
    Prev
    Next
    INDEX
    Explanations

    Meiji Emperor, Peter III, Indian War

    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
    æ½ĩæ´Ĵ
    -0.07
    å·¥ä¼ļ主å¸Ń
    -0.07
    æµĨ
    -0.07
    åIJĴ
    -0.07
    ased
    -0.07
    Powered
    -0.07
    åIJįåī¯
    -0.07
    udara
    -0.07
    ä»İä¸ļ
    -0.07
    å°Ķå¾·
    -0.07
    POSITIVE LOGITS
    åıĺæ³ķ
    0.09
    æĶ¹èī¯
    0.08
    æĭĻ
    0.08
    æĶ¹éĿ©
    0.08
    çݰ代åĮĸ
    0.08
    æĸ°æĶ¿
    0.08
     Transform
    0.08
    æĶ¹éĿ©çļĦ
    0.08
     reform
    0.07
    Transform
    0.07
    Activations Density 0.004%

    No Known Activations