© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14271
    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
     commenting
    -18.13
    comments
    -17.88
    评论
    -17.00
    裁定
    -17.00
     disclosures
    -17.00
    评价
    -16.88
     analytical
    -16.50
    -comment
    -16.50
    -oper
    -16.50
    议论
    -16.38
    POSITIVE LOGITS
     Game
    30.13
    Game
    30.00
     game
    29.63
    游戏
    28.13
    _game
    28.13
    遊戲
    27.13
    _Game
    26.88
     games
    26.38
    游戏中
    26.25
    game
    26.13
    Activations Density 0.360%

    No Known Activations