© 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. 15675
    Prev
    Next
    INDEX
    Explanations

    say austerity

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

    No Comments

    Negative Logits
    ucket
    -17.25
     dbName
    -17.25
     Billboard
    -17.13
    邕
    -16.88
    勇士
    -16.88
    dbName
    -16.25
    eventName
    -16.13
    bomb
    -16.00
    运气
    -16.00
     Glover
    -15.88
    POSITIVE LOGITS
     célib
    19.25
     celib
    19.13
    自律
    18.25
     restrictions
    16.38
     control
    15.94
    克制
    15.75
    斋
    15.56
     austerity
    15.50
    控制
    15.38
     restriction
    15.19
    Activations Density 0.313%

    No Known Activations