© 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. 1796
    Prev
    Next
    INDEX
    Explanations

    [东] => [东]

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

    No Comments

    Negative Logits
    East
    -32.00
     East
    -31.13
     east
    -29.88
    东
    -29.50
     Eastern
    -29.50
    Eastern
    -29.38
     EAST
    -29.13
    east
    -27.25
    -East
    -27.25
    电动
    -27.13
    POSITIVE LOGITS
    玩游戏
    15.81
    -player
    15.38
     play
    15.31
    .sql
    14.75
     SQL
    14.69
     drug
    14.63
     playable
    14.50
    卡
    14.50
    vez
    14.25
    irth
    14.13
    Activations Density 0.155%

    No Known Activations