© 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. 15630
    Prev
    Next
    INDEX
    Explanations

    say "hub"

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

    No Comments

    Negative Logits
    玉米
    -22.63
     Dakota
    -22.25
    茅台
    -21.50
     Wheat
    -21.38
     linen
    -20.75
     maple
    -20.75
     pineapple
    -20.50
     fries
    -20.38
     Colorado
    -20.38
    Colorado
    -19.63
    POSITIVE LOGITS
    枢纽
    19.50
     Resolver
    19.25
    廊
    18.50
    槌
    17.88
    launcher
    17.00
     guidance
    16.75
     impuls
    16.75
     Guidance
    16.63
    (anchor
    16.38
    中枢
    16.38
    Activations Density 0.767%

    No Known Activations