© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1459
    Prev
    Next
    INDEX
    Explanations

    say "surgical"

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

    No Comments

    Negative Logits
     coffee
    -45.75
    咖啡
    -44.50
     Coffee
    -40.50
    Coffee
    -37.25
    coffee
    -37.00
    コーヒー
    -33.50
     Coff
    -28.13
     caffeine
    -27.63
     coff
    -27.13
    コーヒ
    -27.00
    POSITIVE LOGITS
     Surgical
    19.13
    术
    18.38
     surg
    17.88
     surgical
    17.00
    Dynamic
    16.00
    手术
    15.81
     dynamic
    15.56
     Dynamic
    15.19
    疡
    15.19
     socialist
    15.00
    Activations Density 0.047%

    No Known Activations