© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    文明

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

    No Comments

    Negative Logits
    文明
    -42.75
    文明城市
    -25.13
     văn
    -23.88
    civil
    -23.50
     civilization
    -23.38
    文本
    -22.00
     civil
    -21.38
    Civil
    -21.25
     text
    -21.13
    精神文明
    -21.00
    POSITIVE LOGITS
    电台
    15.56
     Lamb
    14.81
    台湾
    14.69
    Gear
    14.25
    db
    14.25
    $db
    14.06
    DB
    13.06
    ibles
    13.00
    药
    13.00
    ']=='
    12.94
    Activations Density 0.050%

    No Known Activations