© 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. 25402
    Prev
    Next
    INDEX
    Explanations

    division, chapter, section or unit name

    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
    åįıä¼ļä¼ļéķ¿
    -0.07
    uten
    -0.07
    Moment
    -0.07
    ä¸Ģå®ļä¸įè¦ģ
    -0.07
     Chec
    -0.06
    æĢ§æł¼å¼ĢæľĹ
    -0.06
    osat
    -0.06
     neger
    -0.06
    yku
    -0.06
    ationally
    -0.06
    POSITIVE LOGITS
    ยà¹Īà¸Ńย
    0.09
    ender
    0.08
    ÏĪη
    0.08
     subsection
    0.07
    بخ
    0.07
    antar
    0.07
    chema
    0.07
    unker
    0.07
    chn
    0.07
    rawl
    0.07
    Activations Density 0.422%

    No Known Activations