© 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. 1648
    Prev
    Next
    INDEX
    Explanations

    [farmers] => [markets]

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

    No Comments

    Negative Logits
    律师
    -23.75
    (logger
    -23.50
    医生
    -23.13
     physician
    -23.13
    科学家
    -23.00
    球员
    -22.75
    logger
    -21.75
    教师
    -21.50
    	logger
    -21.25
    厨师
    -21.25
    POSITIVE LOGITS
    台
    19.88
     sal
    18.38
    sal
    18.00
    臺
    17.38
    盐
    17.00
    _mac
    16.88
     �
    16.50
     salt
    16.50
     Sal
    16.38
    umn
    16.25
    Activations Density 0.407%

    No Known Activations