© 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. 14151
    Prev
    Next
    INDEX
    Explanations

    say "code" terms

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

    No Comments

    Negative Logits
     extension
    -21.88
     extensions
    -21.75
    extension
    -20.00
    配置
    -19.13
    Extension
    -19.13
    (extension
    -19.13
    _extensions
    -19.00
    ��
    -19.00
     practice
    -18.63
    .term
    -18.38
    POSITIVE LOGITS
     cod
    15.81
     orders
    15.31
    合作
    14.94
     modelName
    14.75
    合作关系
    14.69
     cut
    14.56
     col
    14.31
    编码
    14.31
     order
    14.25
     collaboration
    14.19
    Activations Density 0.849%

    No Known Activations