© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    [英语] => [英语]

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

    No Comments

    Negative Logits
    API
    -21.25
    英语
    -20.00
    lambda
    -19.38
     API
    -19.00
     Api
    -17.88
    lang
    -17.88
     Anglo
    -17.88
     lambda
    -17.63
    -api
    -17.63
    羊肉
    -17.50
    POSITIVE LOGITS
    Ill
    16.88
     Sơn
    15.88
    ill
    15.75
    电子
    15.63
    忻
    15.50
    森林
    15.25
    \Console
    15.19
    簸
    15.13
     computer
    15.00
     Logic
    14.94
    Activations Density 0.081%

    No Known Activations