© 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. 1093
    Prev
    Next
    INDEX
    Explanations

    [fuel] => [fuel]

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

    No Comments

    Negative Logits
     fuel
    -50.00
    燃料
    -48.75
     Fuel
    -47.50
    Fuel
    -46.00
    fuel
    -44.75
     fuels
    -41.50
    燃油
    -37.00
     Fu
    -27.88
    燃料电池
    -27.38
     fueled
    -25.38
    POSITIVE LOGITS
    arrays
    15.75
    arda
    15.06
    EDIT
    14.81
    array
    14.44
    icity
    14.19
     arrays
    14.06
     array
    14.00
    edit
    13.94
    鄞
    13.81
    韓
    13.63
    Activations Density 0.059%

    No Known Activations