© 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. 495
    Prev
    Next
    INDEX
    Explanations

    say "legal terms"

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

    No Comments

    Negative Logits
     Budapest
    -21.88
    欧冠
    -20.25
    骑行
    -19.75
     Bicycle
    -18.75
     Mediterranean
    -18.38
    Euro
    -18.38
     bicycle
    -18.25
     channelId
    -18.00
     Bike
    -17.88
     Kiev
    -17.50
    POSITIVE LOGITS
     Court
    25.63
     Justice
    24.50
     justices
    24.25
     courts
    24.13
     court
    23.75
    法官
    23.50
     Courts
    23.13
    Justice
    22.50
     Scalia
    22.38
    法庭
    22.38
    Activations Density 0.123%

    No Known Activations