© 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. 1726
    Prev
    Next
    INDEX
    Explanations

    资本主义

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

    No Comments

    Negative Logits
     kart
    -22.00
    Cart
    -21.25
     CART
    -20.63
     carte
    -20.63
    保险公司
    -19.75
     cartesian
    -19.25
    牛奶
    -19.13
     Kart
    -19.00
    山水
    -18.63
     calculus
    -18.25
    POSITIVE LOGITS
    光
    16.13
    匈奴
    15.56
    材料
    14.81
    金
    14.31
     Book
    14.19
    박
    14.13
    秦国
    14.13
    京
    13.81
    口语
    13.69
    cran
    13.50
    Activations Density 0.042%

    No Known Activations