© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    roof

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

    No Comments

    Negative Logits
    屋顶
    -33.50
     roofs
    -29.63
     roof
    -28.38
     rooft
    -28.25
     Roof
    -27.00
     roofing
    -26.00
    roof
    -24.25
     architecture
    -20.75
     rooftop
    -20.75
     coffee
    -19.75
    POSITIVE LOGITS
    motor
    22.88
    _motor
    22.88
    TOKEN
    22.75
    电机
    22.63
     motor
    22.00
    Mus
    21.75
    mus
    21.38
     TOKEN
    20.63
    _tokens
    20.50
    [token
    20.13
    Activations Density 0.060%

    No Known Activations