© 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. 13933
    Prev
    Next
    INDEX
    Explanations

    say "editor"

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

    No Comments

    Negative Logits
    .Transport
    -16.25
    订单
    -16.00
    Destroyed
    -15.56
    运输
    -15.31
    环球
    -15.31
    売
    -15.19
    滂
    -14.94
     Guinness
    -14.88
    运送
    -14.69
     allocation
    -14.63
    POSITIVE LOGITS
    .Editor
    28.38
     editor
    27.38
    editor
    27.00
     editors
    27.00
    Editor
    25.75
    编辑
    25.50
    _editor
    25.50
     Editor
    25.25
     editing
    25.13
     edit
    24.25
    Activations Density 0.259%

    No Known Activations