© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14217
    Prev
    Next
    INDEX
    Explanations

    say "record"

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

    No Comments

    Negative Logits
    公式
    -17.00
    _formula
    -16.50
    发布会
    -15.88
    发布会上
    -15.69
    $request
    -15.44
    图表
    -15.31
    工委
    -15.19
    院长
    -15.06
    工作室
    -14.94
    实践活动
    -14.94
    POSITIVE LOGITS
    记载
    22.75
    描述
    22.25
     description
    21.75
    载
    21.00
    记录
    20.88
     record
    20.38
    description
    20.13
     loads
    20.00
    Descri
    20.00
    record
    19.88
    Activations Density 0.325%

    No Known Activations