© 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. 1203
    Prev
    Next
    INDEX
    Explanations

    say "metal"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Mormons
    -34.25
     Mormon
    -30.50
     LDS
    -29.00
     Utah
    -28.00
     BYU
    -24.13
     kidneys
    -23.38
     salt
    -22.50
     Latter
    -22.50
     Brigham
    -21.88
    青海省
    -21.75
    POSITIVE LOGITS
    metal
    22.00
     metal
    16.63
    金属
    16.25
    欧洲
    15.56
     Europa
    15.31
    Metal
    15.00
    浮
    15.00
    钢结构
    14.88
     Eu
    14.69
    铁
    14.69
    Activations Density 0.051%

    No Known Activations