© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15774
    Prev
    Next
    INDEX
    Explanations

    say fortress

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

    No Comments

    Negative Logits
    qv
    -20.13
     qa
    -18.13
    qd
    -17.88
    qn
    -17.75
    qe
    -17.63
     quotations
    -17.25
     qi
    -17.13
     qp
    -17.00
    𝑞
    -16.88
     QColor
    -16.75
    POSITIVE LOGITS
     Milit
    21.13
    堡垒
    20.75
     militar
    19.13
    寇
    18.88
     fortress
    18.88
    ark
    18.63
     booster
    18.38
    富力
    18.38
     carc
    18.25
    陵
    18.13
    Activations Density 0.451%

    No Known Activations