© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    say 行业

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    生产能力
    -17.25
    trade
    -15.94
    部
    -15.69
    hx
    -15.06
     Industrial
    -14.88
    =model
    -14.75
    hower
    -14.63
     hx
    -14.50
     trade
    -14.38
     entrepreneur
    -14.38
    POSITIVE LOGITS
    行业
    25.25
    行業
    23.25
    行
    22.50
    行业的
    21.75
    行业中
    21.75
     row
    20.63
    方法
    19.63
    _row
    19.63
     Row
    19.50
    Row
    19.13
    Activations Density 0.047%

    No Known Activations