© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 637
    Prev
    Next
    INDEX
    Explanations

    carbon steel

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

    No Comments

    Negative Logits
    青蛙
    -20.00
    工作站
    -18.63
     skateboard
    -18.38
     mozilla
    -18.13
    GTK
    -17.88
     slam
    -17.88
     wheelchair
    -17.88
    olith
    -17.50
    =device
    -17.38
    镫
    -17.13
    POSITIVE LOGITS
     AIS
    15.19
    AST
    14.25
     propertyName
    13.81
    街
    13.63
    pher
    13.56
     Carolina
    13.44
    .Convert
    13.25
    ast
    13.25
    播
    13.19
    UC
    12.81
    Activations Density 0.054%

    No Known Activations