© 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. 1942
    Prev
    Next
    INDEX
    Explanations

    grammar

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

    No Comments

    Negative Logits
    语法
    -41.75
    Grammar
    -31.63
     grammar
    -31.63
     syntax
    -30.88
     gramm
    -30.13
    语言
    -30.13
    grammar
    -28.63
     Syntax
    -28.25
    Syntax
    -28.25
     Grammar
    -27.25
    POSITIVE LOGITS
    滇
    16.63
    嫦
    15.69
    -light
    15.44
     VIDEO
    15.00
     Pokemon
    14.69
     io
    14.50
    视频
    14.50
    _IOS
    14.31
     Video
    14.25
    /io
    14.25
    Activations Density 0.052%

    No Known Activations