© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15421
    Prev
    Next
    INDEX
    Explanations

    say points

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

    No Comments

    Negative Logits
    广告服务
    -19.25
    蓍
    -17.38
     Advertising
    -17.00
     EDM
    -15.69
     MTV
    -15.56
    Advertising
    -15.44
    LIKELY
    -15.31
    Csv
    -15.19
     designers
    -15.13
     Cary
    -14.94
    POSITIVE LOGITS
    POINTS
    19.13
    考点
    18.25
    points
    18.13
    知识点
    17.75
    存储
    17.38
    -points
    17.00
    固
    17.00
     Points
    16.88
     points
    16.75
    点
    16.63
    Activations Density 0.200%

    No Known Activations