© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    step by step reasoning

    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
    ieb
    -0.08
    ä¸ĭä¸Ģç«ł
    -0.08
    ä¿ĿæĬ¤ä½ľçĶ¨
    -0.08
    enis
    -0.07
    说ä¸Ģåı¥
    -0.07
    羣æŃ£å®ŀçİ°
    -0.07
    丢
    -0.07
    åı¯ä»¥å®ŀçİ°
    -0.07
    è¿Ļç§įæĸ¹å¼ı
    -0.07
    é¢Ĩè·ij
    -0.07
    POSITIVE LOGITS
    åĪĨæŀIJ
    0.11
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.11
    æݨçIJĨ
    0.10
     reasoning
    0.10
     analyzing
    0.09
    ä¸ĢæŃ¥æŃ¥
    0.09
    æİĴæŁ¥
    0.09
    è§Ĥå¯Ł
    0.09
    é¦ĸåħĪ
    0.09
     step
    0.09
    Activations Density 0.030%

    No Known Activations