© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30247
    Prev
    Next
    INDEX
    Explanations

    endings or final items

    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
    ä»Ĭ天å°ıç¼ĸ
    -0.07
     meaning
    -0.07
    ī
    -0.06
     ê·¸ë§Įíģ¼
    -0.06
    oleh
    -0.06
    éĤ£æĺ¯åĽłä¸º
    -0.06
     by
    -0.06
    æĿĸ
    -0.06
    人家
    -0.06
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.06
    POSITIVE LOGITS
    ersen
    0.10
     infine
    0.09
     enfin
    0.09
     наконеÑĨ
    0.09
     finally
    0.09
    Lastly
    0.09
    Finally
    0.09
     Lastly
    0.09
     Finally
    0.09
    æĢ»ä¹ĭ
    0.08
    Activations Density 0.048%

    No Known Activations