© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 43035
    Prev
    Next
    INDEX
    Explanations

    academic writing and summaries

    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
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.08
    åİĭåĢĴ
    -0.08
    koz
    -0.08
    еÑĩи
    -0.08
    æĬ¥è®¯
    -0.08
    leta
    -0.08
    kering
    -0.08
    è¦ģæ±Ĥ被åijĬ
    -0.08
    注åĨĮæĪIJç«ĭ
    -0.08
    otte
    -0.07
    POSITIVE LOGITS
    åĪĩå®ŀåı¯è¡ĮçļĦ
    0.08
    äºĪ以
    0.08
    å¾Ĺåĩº
    0.08
    缸åºĶ
    0.08
    å¹¶æıIJåĩº
    0.07
    详ç»ĨçļĦ
    0.07
    æıIJåĩºäºĨ
    0.07
    äºĪ
    0.07
    缸åºĶçļĦ
    0.07
    åĨį以
    0.07
    Activations Density 0.021%

    No Known Activations