© 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. 942
    Prev
    Next
    INDEX
    Explanations

    international humanitarian law

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

    No Comments

    Negative Logits
    厨
    -20.63
    丐
    -19.50
    ourmet
    -18.00
    酿酒
    -17.63
     cider
    -17.50
    工人
    -17.25
    廚
    -17.13
    毡
    -17.00
     Fantasy
    -16.38
     рецепт
    -16.38
    POSITIVE LOGITS
    (IC
    21.13
     IC
    20.75
    .IC
    18.63
    伊拉克
    17.75
    Iraq
    17.50
     unlawful
    17.00
    叙利亚
    16.63
    _IC
    16.63
    .ic
    16.00
     Cy
    15.94
    Activations Density 0.113%

    No Known Activations