© 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. 16042
    Prev
    Next
    INDEX
    Explanations

    say "religious terms"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ustin
    -20.00
    eneg
    -19.13
    荼
    -18.13
    文化建设
    -18.13
    风机
    -17.88
    izzer
    -17.13
     cinemat
    -17.13
    创新能力
    -17.00
    quin
    -17.00
    标
    -17.00
    POSITIVE LOGITS
     Lords
    20.50
     Lord
    19.63
     Lamb
    18.38
    Lord
    17.88
     Sachs
    17.75
    神圣
    17.13
    alth
    16.88
     relief
    16.38
    拯
    16.00
     saver
    15.81
    Activations Density 0.164%

    No Known Activations