© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4672
    Prev
    Next
    INDEX
    Explanations

    latex environments and math notation

    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
    Negative Logits
    .idea
    -0.09
    à¸ļาล
    -0.07
     siap
    -0.07
     thoại
    -0.07
    odar
    -0.07
    ä¼¼éĶ¦
    -0.07
    ADING
    -0.06
    urado
    -0.06
    artment
    -0.06
    à¸ģà¸Ńฮà¸Ńลà¹Į
    -0.06
    POSITIVE LOGITS
    Ø©
    0.11
    ness
    0.10
    ÙĦ
    0.08
    yson
    0.08
    sl
    0.08
    د
    0.08
    à¹īà¸Ńย
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ìĦľëĬĶ
    0.08
    egl
    0.07
    Activations Density 0.011%

    No Known Activations