© 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. 59757
    Prev
    Next
    INDEX
    Explanations

    common or commonly followed by nouns

    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
    åı¯è¨Ģ
    -0.08
    gian
    -0.08
     обо
    -0.08
    شاÙģ
    -0.08
    éĩįéĩįçļĦ
    -0.08
    uren
    -0.08
    apor
    -0.08
    à¸ŀà¸Ļ
    -0.08
    andola
    -0.07
    icensing
    -0.07
    POSITIVE LOGITS
    ly
    0.11
    åģļæ³ķ
    0.10
    ä¸įè¡°
    0.10
    est
    0.09
    æĥħåĨµä¸ĭ
    0.09
    wealth
    0.09
     sekali
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ÃŃsimo
    0.09
    emente
    0.08
    Activations Density 0.034%

    No Known Activations