© 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. 14394
    Prev
    Next
    INDEX
    Explanations

    say Extension

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

    No Comments

    Negative Logits
    球
    -16.25
    ��
    -16.13
    光影
    -15.25
    steen
    -14.63
    转换
    -14.56
    影
    -14.44
    翻身
    -14.19
    进球
    -14.06
    abble
    -13.88
    ourt
    -13.75
    POSITIVE LOGITS
    Extension
    30.88
     extensions
    30.88
     Extension
    30.63
     extension
    29.50
     Extensions
    29.25
    _extension
    28.13
    extend
    27.38
    extensions
    27.00
     extend
    26.50
    (extension
    26.00
    Activations Density 0.080%

    No Known Activations