© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    seed

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

    No Comments

    Negative Logits
    统计局
    -17.25
    统计
    -16.75
    (calc
    -16.25
    anny
    -16.13
    .xls
    -15.38
    Kansas
    -15.38
    .chart
    -15.13
    Stat
    -14.88
     statistics
    -14.63
    switch
    -14.63
    POSITIVE LOGITS
    肺癌
    20.38
    镖
    19.13
     Hawk
    18.38
    鹰
    17.75
    翡
    17.75
    煤炭
    17.50
    小鸟
    17.25
     hawk
    17.00
    高尔夫
    16.75
    火箭
    16.38
    Activations Density 0.342%

    No Known Activations