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

    Neuronpedia

    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. 15781
    Prev
    Next
    INDEX
    Explanations

    say "play"

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

    No Comments

    Negative Logits
     Signals
    -18.50
    SystemService
    -18.38
    评
    -18.00
     Signal
    -18.00
    Signal
    -17.63
     SIGNAL
    -17.50
     signal
    -17.13
    信息服务
    -17.00
    .getService
    -16.88
    评价
    -16.75
    POSITIVE LOGITS
    游戏
    35.00
    的游戏
    32.50
     play
    32.50
     games
    32.00
    -play
    31.13
     game
    30.88
     Play
    30.50
    -game
    30.13
    玩
    30.00
    Play
    29.38
    Activations Density 0.242%

    No Known Activations