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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14294
    Prev
    Next
    INDEX
    Explanations

    say "probability"

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

    No Comments

    Negative Logits
     support
    -20.50
    .support
    -19.88
    支持
    -19.13
    Support
    -18.75
    _support
    -18.63
    support
    -18.50
     Supporting
    -18.38
     Support
    -18.38
    -support
    -18.13
    upport
    -17.63
    POSITIVE LOGITS
    概率
    25.38
     probability
    24.75
    Probability
    23.88
    风险管理
    23.63
    probability
    22.75
     Probability
    22.50
    Prob
    22.13
    的概率
    21.88
    风险
    21.88
     EventType
    21.88
    Activations Density 0.488%

    No Known Activations