© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3217
    Prev
    Next
    INDEX
    Explanations

    say 派

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    文件
    -16.00
     pov
    -15.63
     Pierce
    -15.19
     CMP
    -15.19
    ais
    -15.06
    -pt
    -14.63
    PM
    -14.38
    _REGION
    -14.13
    绗
    -14.06
    imi
    -14.00
    POSITIVE LOGITS
    派
    27.25
     pair
    20.88
    期内
    20.75
    派人
    19.13
    期
    18.50
    群
    17.38
    Pair
    17.38
    pair
    17.13
    父
    17.13
     parent
    16.88
    Activations Density 0.025%

    No Known Activations