© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    say silicon

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     farm
    -46.50
    Farm
    -45.50
     farms
    -45.25
     Farm
    -44.25
     farming
    -41.50
     farmers
    -40.25
    农场
    -40.00
     Farms
    -39.25
    农
    -39.00
    farm
    -38.00
    POSITIVE LOGITS
     Silicon
    17.88
    二氧化
    16.00
     silicon
    15.75
    alus
    15.50
     Si
    15.50
     Diablo
    15.44
    索尼
    15.13
    Si
    15.13
    ETO
    14.94
     Sony
    14.38
    Activations Density 0.076%

    No Known Activations