© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    division 1, D, stage IV

    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
    odle
    -0.09
    upy
    -0.08
    ëł¹
    -0.08
    åħ¨éĥ¨è¯Ħ论
    -0.08
    à³ģ
    -0.07
    dan
    -0.07
    ses
    -0.07
     mẽ
    -0.07
    วม
    -0.07
    ainte
    -0.07
    POSITIVE LOGITS
    ownt
    0.08
    owntown
    0.08
    ementia
    0.07
    urance
    0.07
    YNAMIC
    0.07
    inet
    0.07
    quo
    0.07
    ijkstra
    0.07
    ungeons
    0.07
    æĸĩæĺĮ
    0.07
    Activations Density 0.003%

    No Known Activations