© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14994
    Prev
    Next
    INDEX
    Explanations

    say "China"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Tud
    -15.94
    .owl
    -15.81
    <tag
    -15.56
    /current
    -15.31
     McGill
    -14.56
     algebra
    -14.50
    焘
    -14.38
    [${
    -14.13
    (SQL
    -14.00
    .timedelta
    -14.00
    POSITIVE LOGITS
    住了
    20.38
    中国
    16.25
    住
    15.06
    京津冀
    14.31
    中国人
    14.25
    }//
    14.19
    oad
    14.19
    中国大陆
    14.00
    justice
    14.00
    �除
    13.94
    Activations Density 0.147%

    No Known Activations