© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16323
    Prev
    Next
    INDEX
    Explanations

    say "flex"

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

    No Comments

    Negative Logits
    THREAD
    -18.75
    安全管理
    -17.25
    铯
    -16.63
     Uran
    -16.50
     THREAD
    -16.13
    墅
    -15.88
     UIL
    -15.69
    錾
    -15.50
    -css
    -15.31
    HTTPRequest
    -15.25
    POSITIVE LOGITS
    Flex
    23.88
    关节
    23.50
     flex
    23.13
     flexibility
    23.00
    灵活性
    22.13
    灵活
    21.88
     Flex
    21.88
    _JO
    21.50
    flex
    21.13
     joint
    20.63
    Activations Density 0.113%

    No Known Activations