© 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. 50654
    Prev
    Next
    INDEX
    Explanations

    identify those

    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
    æĺ¯ä¸Ģ项
    -0.07
    æĺ¯ä¸Ģ件
    -0.07
    Âł
    -0.07
     mol
    -0.07
     metrics
    -0.07
    æŃ¥æŃ¥
    -0.06
    _perc
    -0.06
    ä¸Ģ件
    -0.06
     lang
    -0.06
    æĺ¯ä¸Ģéģĵ
    -0.06
    POSITIVE LOGITS
     enumeration
    0.10
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.10
     representatives
    0.09
     enumerated
    0.09
     enumerate
    0.09
    åĪĹ表
    0.09
     гÑĢÑĥппи
    0.09
     grouping
    0.09
    åħ±äº§
    0.09
    人åijĺåIJįåįķ
    0.09
    Activations Density 0.013%

    No Known Activations