© 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. 14470
    Prev
    Next
    INDEX
    Explanations

    [的] => [的]

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

    No Comments

    Negative Logits
    abble
    -18.38
    -redux
    -17.88
     Bethlehem
    -17.75
     freder
    -17.63
    -NLS
    -17.38
    -widgets
    -17.25
    (machine
    -17.13
    米兰
    -16.75
     unify
    -16.75
    sitemap
    -16.63
    POSITIVE LOGITS
     circ
    15.63
    im
    14.50
    izers
    13.56
    l
    13.38
    Eng
    13.13
    圈
    13.13
    erah
    12.94
    圆
    12.94
    데
    12.56
    ron
    12.38
    Activations Density 0.107%

    No Known Activations