© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15167
    Prev
    Next
    INDEX
    Explanations

    Iberian Peninsula

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

    No Comments

    Negative Logits
    化学品
    -20.75
    ched
    -17.75
    GRADE
    -17.63
    grades
    -17.13
    ocha
    -17.00
    usch
    -16.75
    雨
    -16.75
    CHED
    -16.50
    uur
    -16.38
    chet
    -16.25
    POSITIVE LOGITS
    西班牙
    25.00
    Spain
    22.50
     Spain
    22.50
     Span
    22.38
    .Span
    21.25
    /span
    20.50
    _span
    20.38
     Spanish
    19.75
     span
    19.63
     España
    19.63
    Activations Density 0.128%

    No Known Activations