© 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. 345
    Prev
    Next
    INDEX
    Explanations

    say "initialisms"

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

    No Comments

    Negative Logits
    云南省
    -51.00
     Myanmar
    -49.25
    昆明
    -46.75
    滇
    -46.00
    云南
    -45.50
    缅甸
    -45.25
     Thai
    -43.25
     Laos
    -43.00
     Kosovo
    -42.75
     Vietnamese
    -42.25
    POSITIVE LOGITS
    口水
    14.94
    岬
    14.94
     Sanford
    13.88
    箩
    13.75
     TF
    13.69
     Tf
    13.69
    Authenticate
    13.25
    圣地
    13.13
     Mach
    13.00
    阿根
    12.88
    Activations Density 1.073%

    No Known Activations