© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    say sculpture

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

    No Comments

    Negative Logits
    .getWindow
    -17.50
    AllWindows
    -16.88
    证券交易
    -16.00
    getWindow
    -15.75
     packet
    -15.44
    帘
    -15.38
    TagName
    -15.38
    strings
    -15.19
     McCart
    -15.00
    ARGIN
    -14.88
    POSITIVE LOGITS
    雕塑
    30.50
     sculptures
    28.50
    雕刻
    28.38
     sculpt
    28.13
    雕像
    28.00
     statues
    27.13
     sculpture
    27.00
     Sculpt
    26.00
     statue
    24.25
     Statue
    21.50
    Activations Density 0.438%

    No Known Activations