© 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. 556
    Prev
    Next
    INDEX
    Explanations

    say "UN"

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

    No Comments

    Negative Logits
    合肥市
    -20.13
    Pokemon
    -19.88
    =torch
    -19.38
    滁
    -19.25
    泰州
    -19.25
     Milwaukee
    -19.13
    砀
    -18.88
     Pokemon
    -18.75
    Oregon
    -18.50
    福州
    -18.38
    POSITIVE LOGITS
     UN
    37.50
    联合国
    33.00
    UN
    29.88
    	UN
    22.88
     UT
    22.25
     VN
    21.88
     Libyan
    21.00
    VN
    20.13
    .UN
    19.75
     UNESCO
    19.75
    Activations Density 0.209%

    No Known Activations