© 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. 31126
    Prev
    Next
    INDEX
    Explanations

    portions and fractions

    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
    pa
    -0.07
    æīĭæľºçīĪ
    -0.06
    çľĭ
    -0.06
     quê
    -0.06
    ItemList
    -0.06
    ศ
    -0.06
    orges
    -0.06
     limits
    -0.06
    åıªçľĭ
    -0.06
    æĪIJéķ¿
    -0.06
    POSITIVE LOGITS
     ÙħÙĨÙĩÙħ
    0.11
     davon
    0.10
     diantaranya
    0.10
    ä¸Ģéĥ¨åĪĨ
    0.09
     ÙħÙĨÙĩا
    0.09
     diantara
    0.09
     portion
    0.09
     hierv
    0.09
     spoÅĽród
    0.08
    à¸Ńยà¹Īาà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    Activations Density 0.488%

    No Known Activations