© 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. 60019
    Prev
    Next
    INDEX
    Explanations

    during

    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
    alisi
    -0.07
    è¿Ļç§įäºĭ
    -0.07
     hinweg
    -0.07
    樱
    -0.07
    ä»ĸ身ä¸Ĭ
    -0.06
    ิà¹Īà¸Ļ
    -0.06
    asarkan
    -0.06
    ::$_
    -0.06
    ãģ°
    -0.06
    åħ¨èĥľ
    -0.06
    POSITIVE LOGITS
     during
    0.26
    during
    0.24
     During
    0.22
     durante
    0.22
    During
    0.22
     tijdens
    0.18
     أثÙĨاء
    0.16
     durant
    0.16
     während
    0.16
    à¹ĥà¸Ļà¸Ĭà¹Īวà¸ĩ
    0.15
    Activations Density 1.369%

    No Known Activations