© 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. 14310
    Prev
    Next
    INDEX
    Explanations

    say "supply"

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

    No Comments

    Negative Logits
    显示器
    -16.63
    Recognizer
    -16.50
    ประต
    -16.38
    插入
    -15.94
    /template
    -15.25
    设计
    -15.06
    (insert
    -14.94
     ePub
    -14.81
     môi
    -14.69
     Listener
    -14.50
    POSITIVE LOGITS
    供应
    44.50
     supply
    44.00
     Supply
    42.00
    Supply
    42.00
     supplies
    38.75
    供给
    38.50
    supply
    38.50
    _supply
    38.00
     Supplies
    34.50
     supplying
    32.75
    Activations Density 1.026%

    No Known Activations