© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 307
    Prev
    Next
    INDEX
    Explanations

    say accented letters

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

    No Comments

    Negative Logits
    秦皇岛
    -23.38
    香蕉
    -19.13
     Jamaica
    -18.75
    虹桥
    -18.00
    大庆
    -17.88
    蜈
    -17.50
    在上海
    -17.25
    狮子
    -17.13
    唐山
    -17.13
     Sakura
    -16.50
    POSITIVE LOGITS
     Ö
    36.00
     Ç
    35.00
     Á
    34.50
     ç
    34.00
     ö
    33.75
    Í
    33.50
     í
    33.25
    í
    33.00
     á
    32.25
    Ö
    32.25
    Activations Density 0.182%

    No Known Activations