© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    [衣] => [食]

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

    No Comments

    Negative Logits
    衣物
    -39.75
    衣
    -38.75
    衣服
    -37.75
     CSS
    -37.25
     clothing
    -37.25
     clothes
    -35.75
    Css
    -35.50
     css
    -35.50
    的衣服
    -35.50
    CSS
    -34.50
    POSITIVE LOGITS
    	Py
    18.25
    引擎
    17.88
     engine
    17.88
    -pol
    17.75
     motor
    17.25
    =torch
    17.25
    ENGINE
    17.13
    engine
    17.13
    .engine
    17.00
    /engine
    16.63
    Activations Density 0.122%

    No Known Activations