© 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. 20439
    Prev
    Next
    INDEX
    Explanations

    decimal conversion

    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
    Ñī
    -0.08
    evo
    -0.07
    iro
    -0.07
    otland
    -0.07
    alo
    -0.07
    翻天
    -0.07
    éĢīæĭ©ä¸įåIJĮçļĦ
    -0.07
     tight
    -0.07
    åĮ»çĸĹä¿Ŀåģ¥
    -0.07
    ocol
    -0.06
    POSITIVE LOGITS
     conversion
    0.10
     Converted
    0.10
     Conversion
    0.10
     conversions
    0.09
     Converts
    0.09
    Convert
    0.09
     converts
    0.09
    转æį¢
    0.09
     Convert
    0.09
    convert
    0.09
    Activations Density 0.005%

    No Known Activations