© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13970
    Prev
    Next
    INDEX
    Explanations

    mother tongue

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

    No Comments

    Negative Logits
    WISE
    -18.63
    木材
    -15.44
    NodeType
    -15.38
    Traits
    -15.31
     arson
    -15.25
    药材
    -15.00
    柱
    -14.94
    茶园
    -14.88
     stove
    -14.88
    Wood
    -14.81
    POSITIVE LOGITS
    语言
    58.25
     language
    54.25
    的语言
    53.50
    語言
    50.50
     Language
    50.25
     languages
    48.75
    Language
    47.50
     lang
    47.25
    language
    46.75
     Languages
    46.00
    Activations Density 1.285%

    No Known Activations