© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14644
    Prev
    Next
    INDEX
    Explanations

    English civil war

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

    No Comments

    Negative Logits
    inka
    -18.38
    钒
    -17.25
    nga
    -17.13
    labels
    -16.50
    uer
    -16.50
    zos
    -16.25
    indexed
    -16.25
     labels
    -16.25
    imb
    -16.13
    .uf
    -16.13
    POSITIVE LOGITS
    洁净
    15.38
    품
    14.50
    剧中
    14.50
    洁
    14.31
     toler
    13.63
    olly
    13.50
    净化
    13.44
    etest
    13.44
    协议
    13.38
     Parl
    13.25
    Activations Density 0.131%

    No Known Activations