© 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. 37490
    Prev
    Next
    INDEX
    Explanations

    foreign prefixes, suffixes, or abbreviations

    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
    æķħèĢĮ
    -0.08
    tees
    -0.08
    endoza
    -0.07
    åĽłä¸ºæĪij
    -0.07
    设å¤ĩå®īè£ħ
    -0.07
     Ganze
    -0.07
    ikli
    -0.07
    zos
    -0.07
    iente
    -0.07
    (&(
    -0.07
    POSITIVE LOGITS
    à¸ĭึà¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ
    0.13
    —the
    0.12
    —a
    0.12
     à¸ĭึà¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ
    0.11
    —an
    0.10
    ä¹Łå°±æĺ¯
    0.09
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.09
    ï¼Ī
    0.09
     selaku
    0.09
    —who
    0.08
    Activations Density 1.002%

    No Known Activations