© 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. 51
    Prev
    Next
    INDEX
    Explanations

    say "Russian" words

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

    No Comments

    Negative Logits
    (xy
    -20.00
    荥
    -18.63
    溧
    -18.13
    JKLM
    -17.25
    �
    -17.00
     ij
    -16.88
    张某
    -16.88
    轵
    -16.50
    陈某
    -16.50
    ijk
    -16.50
    POSITIVE LOGITS
     Russian
    51.00
     Russia
    49.50
    俄罗斯
    49.00
     Russians
    48.50
    Russia
    46.25
    Russian
    45.50
     Russ
    41.25
    普京
    41.25
    俄
    40.00
    俄军
    39.75
    Activations Density 0.157%

    No Known Activations