© 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. 63822
    Prev
    Next
    INDEX
    Explanations

    units of measurement (mol, L, M)

    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
    èĸĩ
    -0.07
     ξη
    -0.07
    æĺ¾å¾ĹæĽ´åĬł
    -0.07
    _IV
    -0.07
    imulator
    -0.07
    itto
    -0.07
    _scope
    -0.07
     Rad
    -0.06
     Rubin
    -0.06
     ÙħØ·
    -0.06
    POSITIVE LOGITS
    æĿŀ
    0.07
    rick
    0.07
    asha
    0.07
    æ²
    0.07
    jsonp
    0.07
    çŁ³æ¦´
    0.06
    å³¥
    0.06
    aza
    0.06
    anta
    0.06
     Conversion
    0.06
    Activations Density 0.003%

    No Known Activations