© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    [cart] => [cartilage]

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

    No Comments

    Negative Logits
     cart
    -60.00
    Cart
    -55.25
     Cart
    -53.25
    cart
    -52.25
    _cart
    -51.75
    -cart
    -48.50
     CART
    -48.25
     carts
    -47.75
    .cart
    -47.50
    (cart
    -46.50
    POSITIVE LOGITS
     asymmetric
    14.69
     Angie
    14.56
    ymmetric
    14.50
    ABI
    14.25
    PB
    14.25
    天花
    14.06
    瑜
    13.56
    Security
    13.38
     security
    13.25
    激光
    13.25
    Activations Density 0.055%

    No Known Activations