© 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. 687
    Prev
    Next
    INDEX
    Explanations

    say Norwegian words

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

    No Comments

    Negative Logits
    皖
    -18.13
     Midlands
    -18.13
    黟
    -17.88
    亳
    -17.50
    徽
    -17.00
    徐州
    -16.75
     Amber
    -15.50
     Midwest
    -15.44
     McMaster
    -15.38
    阜阳
    -15.31
    POSITIVE LOGITS
     ila
    20.50
     uten
    20.38
     av
    20.13
     og
    20.00
    fte
    19.00
     OG
    18.00
    蔺
    17.88
    ಲ
    17.75
     bruk
    17.63
     søker
    17.38
    Activations Density 0.008%

    No Known Activations