© 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. 1668
    Prev
    Next
    INDEX
    Explanations

    [any] => beans

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

    No Comments

    Negative Logits
     beans
    -36.50
     Beans
    -33.50
    Beans
    -32.00
    豆
    -32.00
    Bean
    -30.13
     Bean
    -30.00
     bean
    -29.13
    beans
    -25.88
    大豆
    -24.50
    (bean
    -24.38
    POSITIVE LOGITS
     Ireland
    20.25
    湖北
    19.88
     Irish
    19.63
    湖北省
    18.88
    爱尔兰
    18.38
    武汉市
    18.25
    武汉
    17.88
     Irma
    17.38
    楚
    17.38
    .slice
    16.63
    Activations Density 0.061%

    No Known Activations