© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1307
    Prev
    Next
    INDEX
    Explanations

    say "宫 compounds"

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

    No Comments

    Negative Logits
    宫
    -38.25
    宫殿
    -37.75
    宮
    -36.75
     palace
    -33.00
     Palace
    -30.88
    皇宫
    -29.75
     widget
    -27.38
    (widget
    -27.00
     gal
    -26.88
    widget
    -26.13
    POSITIVE LOGITS
    	vector
    17.88
     vector
    17.75
     computation
    17.13
    /vector
    16.63
    计算
    16.25
     computations
    16.00
    (vector
    15.88
    計算
    15.88
     Ryder
    15.75
    细菌
    15.69
    Activations Density 0.069%

    No Known Activations