© 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. 16175
    Prev
    Next
    INDEX
    Explanations

    say "big"

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

    No Comments

    Negative Logits
    _skin
    -16.63
     Stamina
    -16.63
    claimer
    -16.13
     cls
    -16.13
    .Validation
    -15.56
     scrub
    -15.50
     Soft
    -15.25
     casual
    -15.13
     Russo
    -15.00
    质量安全
    -14.88
    POSITIVE LOGITS
    最大
    20.50
    最大的
    16.63
    Program
    16.50
    的最大
    16.00
    程序
    15.69
    ubi
    15.69
    比较大
    15.69
    JsonValue
    15.63
    越大
    15.56
     maximum
    15.44
    Activations Density 0.172%

    No Known Activations