© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15506
    Prev
    Next
    INDEX
    Explanations

    say party terminology

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

    No Comments

    Negative Logits
    札
    -16.25
    AutoSize
    -16.00
    節
    -14.88
    帘
    -14.81
    Capacity
    -14.81
    ��
    -14.75
    つけ
    -14.69
    cimal
    -14.25
    缶
    -14.19
     spel
    -13.94
    POSITIVE LOGITS
    党员
    22.88
    党组织
    20.00
    党建
    19.38
    党建工作
    19.00
    党组
    19.00
    党的领导
    18.75
    思想政治
    18.75
     Đảng
    18.63
    党支部
    18.63
    党委
    18.38
    Activations Density 0.254%

    No Known Activations