© 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. 1808
    Prev
    Next
    INDEX
    Explanations

    say "countries"

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

    No Comments

    Negative Logits
     Toro
    -21.00
     gå
    -18.38
    寸
    -18.00
    地坪
    -17.25
    如果玩家
    -16.88
     meg
    -16.75
    滔
    -16.50
    直销
    -16.38
    -</
    -16.38
     payday
    -16.38
    POSITIVE LOGITS
     English
    13.63
    是中国
    13.31
     Ireland
    13.19
     Danish
    12.56
    .gc
    12.31
    在中国
    12.13
    代理
    12.06
    noise
    12.06
     Spanish
    11.94
     European
    11.88
    Activations Density 0.124%

    No Known Activations