© 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. 13920
    Prev
    Next
    INDEX
    Explanations

    say cases

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

    No Comments

    Negative Logits
    /terms
    -18.13
    表达
    -17.88
     TERMS
    -17.00
    模板
    -16.88
    _EXPR
    -16.88
    terms
    -16.75
     Terms
    -16.75
     templates
    -16.50
     terms
    -16.50
     Template
    -16.00
    POSITIVE LOGITS
    病例
    25.63
    报告
    24.88
    cases
    24.63
    _cases
    24.38
     case
    24.38
     cases
    24.38
    case
    23.88
    Case
    23.63
     reporting
    23.13
    _CASE
    22.50
    Activations Density 0.325%

    No Known Activations