© 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. 49726
    Prev
    Next
    INDEX
    Explanations

    functions may, wrap can, industry you, site certainly, beam passes, doctor informs

    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
    åįļæĸĩ
    -0.07
    ä¹ŁæĮº
    -0.06
     valt
    -0.06
    个人认为
    -0.06
    æĹłåıĮ
    -0.06
    amoto
    -0.06
    ä¹ŁæŃ£
    -0.06
    åIJĪãģĦ
    -0.06
    ÑĦов
    -0.06
    кÑĢаÑĤно
    -0.06
    POSITIVE LOGITS
    å¦Ĥæŀľ
    0.13
     যদি
    0.12
    å¦Ĥæŀľåıªæĺ¯
    0.12
    å¾Ģå¾Ģ
    0.12
    åı¯ä»¥æĺ¯
    0.12
    èĭ¥
    0.11
     usually
    0.11
     often
    0.11
    èĭ¥æĺ¯
    0.11
    æľĢ好æĺ¯
    0.11
    Activations Density 0.226%

    No Known Activations