© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    say "computer"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    \
↵
    -20.00
    /portfolio
    -18.38
    <?↵
    -17.75
     upholstery
    -17.50
     garment
    -17.38
     Freight
    -17.38
    玉石
    -17.13
     acrylic
    -17.00
     freight
    -17.00
     quarry
    -17.00
    POSITIVE LOGITS
    操作系统
    18.38
    计算机
    16.63
     结
    16.00
    灵
    15.00
    环
    14.75
    机
    14.31
    保护
    13.94
    子
    13.88
    数据
    13.69
    处理
    13.63
    Activations Density 0.097%

    No Known Activations