© 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. 26458
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence endings

    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
    ä¹Łæĺ¯ä¸ª
    -0.10
     itself
    -0.09
    ä¸ĢèģĮ
    -0.09
    ä¸īæĸ¹
    -0.09
    æĺ¯ä¸ª
    -0.08
    å¤ļç§įæĸ¹å¼ı
    -0.08
    ä¸Ģè¯į
    -0.08
    ä¹Łæĺ¯ä¸Ģ个
    -0.08
    ä¸īåŃĹ
    -0.08
    å¤ļæĸ¹
    -0.08
    POSITIVE LOGITS
     respectively
    0.24
    åIJĦèĩªçļĦ
    0.23
    åIJĦèĩª
    0.23
    ãģĿãĤĮãģŀãĤĮ
    0.22
    åĪĨåĪ«æĺ¯
    0.22
     ê°ģê°ģ
    0.22
    åĪĨåĪ«
    0.21
    è¿Ļ两个
    0.21
    åĪĨåĪ«ä¸º
    0.21
    åĪĨåĪ¥
    0.18
    Activations Density 0.797%

    No Known Activations