© 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. 16143
    Prev
    Next
    INDEX
    Explanations

    say "frequency adverbs"

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

    No Comments

    Negative Logits
    ucas
    -17.13
    iale
    -17.00
    kok
    -16.88
    梨
    -16.63
     Colbert
    -16.63
    炬
    -16.13
    峨
    -16.00
    乾坤
    -16.00
    metros
    -15.88
    犁
    -15.06
    POSITIVE LOGITS
    频率
    40.25
     frequency
    38.50
     frequencies
    36.75
    频
    36.00
     freq
    35.75
    frequency
    35.25
     Frequency
    35.00
    freq
    35.00
    Frequency
    34.75
    (freq
    32.75
    Activations Density 0.404%

    No Known Activations