© 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. 42089
    Prev
    Next
    INDEX
    Explanations

    token followed by of

    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
    çļĦ好åĿı
    -0.06
    ÑĢÑĥбе
    -0.06
    åĨį好
    -0.06
    æĪijèĩªå·±çļĦ
    -0.06
    áĭį
    -0.06
    æĥ£
    -0.06
    ovsky
    -0.06
    lis
    -0.06
    å¤ļåĸĿ
    -0.06
    osse
    -0.05
    POSITIVE LOGITS
     của
    0.09
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    0.08
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.08
     of
    0.08
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.08
    Ú¯ÙĪÛĮ
    0.08
     TÃī
    0.08
    à¹ģรà¸ģà¸Ĥà¸Ńà¸ĩ
    0.08
    æľĿ天
    0.08
    à¹Ģà¸Ļืà¹īà¸Ńหาà¸Ĥà¸Ńà¸ĩ
    0.08
    Activations Density 1.147%

    No Known Activations