© 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. 1772
    Prev
    Next
    INDEX
    Explanations

    say language

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

    No Comments

    Negative Logits
     STOCK
    -16.88
     stock
    -16.63
    戏
    -16.13
     Yankee
    -15.19
     Palest
    -15.06
    校园
    -14.94
    囡
    -14.75
    Stock
    -14.50
     stocks
    -14.38
    bias
    -14.38
    POSITIVE LOGITS
    语言
    24.25
    _lng
    21.50
    河西
    20.88
     Language
    20.75
     language
    20.50
    的语言
    20.50
    Language
    19.88
    語言
    19.38
     Cardinals
    19.38
    牛肉
    19.13
    Activations Density 0.394%

    No Known Activations