© 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. 14810
    Prev
    Next
    INDEX
    Explanations

    great people

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

    No Comments

    Negative Logits
    矿区
    -19.25
    unicip
    -18.38
    墅
    -18.25
     neighbourhood
    -18.00
     Communities
    -17.50
    代表团
    -17.13
    经纪
    -17.13
    人居环境
    -16.75
    口岸
    -16.75
    ynth
    -16.75
    POSITIVE LOGITS
    的伟大
    17.88
     Nietzsche
    17.38
    天才
    16.75
    英雄
    16.13
    伟大的
    16.00
    高尔
    15.69
    伟
    15.44
    伟大
    15.38
     heroes
    15.31
     Born
    15.25
    Activations Density 0.296%

    No Known Activations