© 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. 15679
    Prev
    Next
    INDEX
    Explanations

    say "wine"

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

    No Comments

    Negative Logits
    elta
    -17.63
    管理模式
    -17.25
     Schema
    -17.13
    治理体系
    -17.00
    eldon
    -16.63
    -services
    -16.63
    LoginForm
    -16.38
    ervices
    -16.25
    /schema
    -16.13
    icts
    -16.00
    POSITIVE LOGITS
    红酒
    26.38
    酿酒
    25.75
    葡萄酒
    25.38
    酒
    25.13
     wine
    25.00
     Wine
    22.50
     grape
    22.25
     wines
    21.63
    白酒
    21.38
     vin
    21.13
    Activations Density 0.108%

    No Known Activations