© 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. 1391
    Prev
    Next
    INDEX
    Explanations

    say fuel

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

    No Comments

    Negative Logits
     Vietnamese
    -38.00
    Viet
    -36.25
     Vietnam
    -33.00
    越南
    -29.13
     viet
    -28.88
     Viet
    -25.75
    韓
    -21.50
    东南亚
    -21.38
     Nguyen
    -20.88
    Thai
    -20.75
    POSITIVE LOGITS
    -google
    19.63
    谷歌
    18.38
    燃料
    17.88
     fuel
    17.13
     Fuel
    16.75
    燃油
    16.50
    fst
    16.00
    _ENGINE
    15.81
     Google
    15.69
     Engines
    15.69
    Activations Density 0.070%

    No Known Activations