© 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. 691
    Prev
    Next
    INDEX
    Explanations

    say names

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

    No Comments

    Negative Logits
     Leeds
    -24.25
     Oxford
    -23.88
    爱尔兰
    -23.75
     Irish
    -23.38
     £
    -23.38
     Yorkshire
    -23.25
     Leicester
    -22.38
    英国
    -22.38
     Birmingham
    -21.75
     Thames
    -21.63
    POSITIVE LOGITS
     Johan
    21.13
     Hugo
    18.88
     Erik
    18.88
    下雨
    18.00
     Georg
    17.13
     Emil
    17.13
     Pedro
    16.88
     Gust
    16.75
    正版
    16.50
     Kong
    16.38
    Activations Density 0.125%

    No Known Activations