© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    say "李"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     axis
    -13.88
     date
    -13.75
    _sidebar
    -13.13
    いただいて
    -13.13
    .currentTarget
    -12.94
    pod
    -12.94
    NodeType
    -12.94
    clearfix
    -12.88
    WAY
    -12.88
    edo
    -12.75
    POSITIVE LOGITS
    李
    55.00
    张
    32.00
    張
    26.25
     �
    25.38
    刘
    24.00
    李先生
    23.88
    杨
    23.88
    赵
    23.25
    王
    23.00
     P
    22.50
    Activations Density 0.114%

    No Known Activations