© 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. 463
    Prev
    Next
    INDEX
    Explanations

    say "After"

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

    No Comments

    Negative Logits
    湖州
    -21.13
     Toledo
    -20.13
    (tt
    -18.63
     WW
    -18.25
     TG
    -18.13
    北宋
    -18.00
    (bb
    -17.50
    歙
    -17.25
     Tur
    -17.25
    汝
    -17.00
    POSITIVE LOGITS
    茂名
    23.00
    珠江
    22.63
    广州市
    22.25
     Riyadh
    22.13
    南沙
    22.13
     Ghana
    21.88
     Yemen
    21.75
     Sakura
    21.63
    Saudi
    21.25
    黑龙江省
    21.13
    Activations Density 0.105%

    No Known Activations