© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1532
    Prev
    Next
    INDEX
    Explanations

    bread

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

    No Comments

    Negative Logits
    布拉
    -15.38
    豆腐
    -15.31
     column
    -15.31
     graph
    -14.75
     JDBC
    -14.69
    布
    -14.63
     Java
    -14.06
     bread
    -14.06
    brew
    -13.94
     Indones
    -13.81
    POSITIVE LOGITS
    电机
    22.50
    鱼
    22.25
    魚
    21.63
    mus
    20.13
     engineer
    20.00
    fish
    19.88
     Chemical
    19.88
    engine
    19.88
     fish
    19.88
     Engine
    19.88
    Activations Density 0.235%

    No Known Activations