© 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. 15701
    Prev
    Next
    INDEX
    Explanations

    say flow

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

    No Comments

    Negative Logits
    宝石
    -22.75
    镯
    -22.63
    锤
    -22.50
    水晶
    -21.25
     crystal
    -21.25
    钻石
    -20.50
     bracelet
    -20.38
     crystall
    -20.25
     crystals
    -20.13
    钢琴
    -19.75
    POSITIVE LOGITS
     FileAccess
    19.88
     airflow
    19.38
    Interop
    19.25
    通畅
    19.13
    互联互通
    19.00
    通
    17.75
    拥堵
    17.75
    网通
    17.63
    畅通
    17.63
     flux
    17.63
    Activations Density 1.170%

    No Known Activations