© 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. 1969
    Prev
    Next
    INDEX
    Explanations

    language

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

    No Comments

    Negative Logits
    语言
    -73.50
     language
    -67.50
     Language
    -64.50
    Language
    -63.00
    的语言
    -60.25
    語言
    -59.50
    language
    -59.25
     languages
    -57.50
    _language
    -55.00
     Languages
    -54.50
    POSITIVE LOGITS
    巢
    19.50
     CD
    16.38
    ทอง
    15.94
     gold
    15.56
    金
    15.13
    CD
    15.13
    -google
    15.06
    桂花
    14.63
    竞选
    14.19
     Circuit
    14.06
    Activations Density 0.253%

    No Known Activations