© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16217
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    3
    -54.25
     three
    -43.25
    3
    -40.75
    three
    -38.25
     Three
    -37.75
     third
    -37.00
    三是
    -36.00
     trois
    -35.25
    三人
    -35.00
     três
    -34.75
    POSITIVE LOGITS
    八个
    20.63
     sixteen
    17.88
     eight
    17.63
     ninth
    17.38
    七个
    16.25
     eighth
    16.13
     fourteen
    15.69
    七八
    15.50
    atti
    15.25
    dzi
    14.94
    Activations Density 0.975%

    No Known Activations