© 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. 18792
    Prev
    Next
    INDEX
    Explanations

    except

    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
    antu
    -0.07
    人æĦı
    -0.07
    ÐłÐ¢
    -0.06
    å°ıèĢĮ
    -0.06
    æĭ¯
    -0.06
    äºĨä¸Ģ份
    -0.06
    Ĵ
    -0.06
     ed
    -0.06
    åĪĨ离åĻ¨
    -0.06
    临走
    -0.06
    POSITIVE LOGITS
     except
    0.11
    Except
    0.10
     kecuali
    0.10
    except
    0.09
     Except
    0.08
    _except
    0.08
     uniform
    0.08
    ä¸įæĸŃçļĦ
    0.07
    éĻ¤äºĨ
    0.07
    填满
    0.07
    Activations Density 0.022%

    No Known Activations