© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1779
    Prev
    Next
    INDEX
    Explanations

    crop

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

    No Comments

    Negative Logits
     crops
    -37.50
     crop
    -37.25
     Crop
    -31.38
    crop
    -31.13
    Crop
    -30.25
    _crop
    -28.75
    作物
    -28.63
    .crop
    -25.00
     cropped
    -24.75
     cropping
    -24.38
    POSITIVE LOGITS
    xml
    18.25
    钢铁
    17.25
     angels
    17.00
     Hezbollah
    17.00
     xml
    17.00
    音乐
    16.88
     Artificial
    16.75
    音乐会
    16.75
    Xml
    16.63
    电工
    16.63
    Activations Density 0.062%

    No Known Activations