© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15872
    Prev
    Next
    INDEX
    Explanations

    say "fire" words

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

    No Comments

    Negative Logits
    دول
    -16.88
    vertices
    -16.75
    徐州
    -16.00
     vertices
    -15.69
    枢纽
    -15.63
    Vertices
    -15.56
    lü
    -15.31
    grades
    -15.19
    vertex
    -15.00
    .Vertex
    -14.94
    POSITIVE LOGITS
     burn
    51.75
     burns
    49.75
    燃烧
    48.75
    火
    48.00
     burning
    48.00
    烧
    47.50
    火焰
    47.25
     fire
    46.50
    burn
    45.75
     flames
    45.75
    Activations Density 0.484%

    No Known Activations