© 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. 1800
    Prev
    Next
    INDEX
    Explanations

    say "games"

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

    No Comments

    Negative Logits
    tensor
    -15.69
    Tensor
    -15.56
     Christian
    -15.13
     tensor
    -14.63
    .tensor
    -14.44
    .Tensor
    -14.38
     Torch
    -14.25
    IColor
    -14.19
    lish
    -13.56
     torch
    -13.44
    POSITIVE LOGITS
     gameId
    21.63
    游戏
    20.00
     game
    20.00
     GAME
    19.88
    遊戲
    19.75
    _Game
    19.50
    Game
    19.38
    游戏中
    19.13
     camera
    18.50
    <Game
    18.50
    Activations Density 0.319%

    No Known Activations