© 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. 196
    Prev
    Next
    INDEX
    Explanations

    say "Russia" terms

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

    No Comments

    Negative Logits
     buffalo
    -20.13
    印尼
    -20.00
     Trinidad
    -19.50
    兖
    -19.50
     Caj
    -19.00
    筠
    -18.50
    华东
    -18.38
     Indies
    -18.25
    畲
    -18.13
     Tamb
    -17.63
    POSITIVE LOGITS
    俄军
    23.13
     Putin
    20.38
    Putin
    20.25
    普京
    18.25
    基辅
    17.75
    俄国
    17.50
     Kiev
    17.25
     NATO
    17.00
     Netanyahu
    16.63
     Russian
    16.50
    Activations Density 0.113%

    No Known Activations