© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    game

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

    No Comments

    Negative Logits
    游戏
    -65.50
     game
    -61.75
     games
    -59.50
     Game
    -57.00
    游戏中
    -56.25
     Games
    -54.75
    Game
    -54.50
    遊戲
    -54.25
    的游戏
    -54.00
    game
    -53.25
    POSITIVE LOGITS
     Pdf
    14.63
    цев
    13.69
    fiber
    13.69
    pdf
    13.38
    ubber
    13.38
    ộc
    13.06
     Bols
    12.88
    ussia
    12.56
    给您
    12.56
    izar
    12.50
    Activations Density 0.134%

    No Known Activations