© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1702
    Prev
    Next
    INDEX
    Explanations

    do not say capital

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    capital
    -29.75
    资本
    -29.63
     capital
    -29.50
    Capital
    -28.38
     Capital
    -28.25
     CAPITAL
    -25.63
     capitalism
    -21.75
    -capital
    -21.38
     Capitals
    -21.13
     capitalize
    -20.38
    POSITIVE LOGITS
     Moon
    16.75
    wx
    16.50
     pdf
    16.13
     tree
    16.13
    =wx
    15.88
    TreeNode
    15.56
    tree
    15.44
    月
    15.31
     trees
    15.13
     moon
    15.06
    Activations Density 0.093%

    No Known Activations