© 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. 7190
    Prev
    Next
    INDEX
    Explanations

    opening quotation or apostrophe

    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
    دÙĬØ©
    -0.07
    人æĿ¥è¯´
    -0.07
    imon
    -0.07
    ellas
    -0.07
    arana
    -0.07
    anke
    -0.06
     alun
    -0.06
    erot
    -0.06
    .undefined
    -0.06
    说çĻ½äºĨ
    -0.06
    POSITIVE LOGITS
    !».
    0.07
    ä¸į好äºĨ
    0.06
    æŁIJæŁIJ
    0.06
    ä¸Ģ声
    0.06
    èĭį穹
    0.06
    èĩªå·²
    0.06
    好åķĬ
    0.06
    ä¸Ĭåİ»
    0.06
    幸äºı
    0.06
    ubles
    0.06
    Activations Density 0.234%

    No Known Activations