© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15542
    Prev
    Next
    INDEX
    Explanations

    say game

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

    No Comments

    Negative Logits
    妇
    -16.63
    化肥
    -16.25
    婦
    -16.25
    dent
    -15.81
    actory
    -15.63
     thrift
    -15.63
    勺
    -15.31
    妇女
    -15.00
     handleMessage
    -14.75
    �
    -14.56
    POSITIVE LOGITS
    游戏
    53.00
     games
    50.25
     game
    49.75
    游戏中
    48.00
    -game
    47.00
    的游戏
    46.50
    games
    45.75
    遊戲
    45.50
    game
    45.00
    _game
    45.00
    Activations Density 0.287%

    No Known Activations