© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14700
    Prev
    Next
    INDEX
    Explanations

    [any] => G

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    qu
    -26.13
     qu
    -25.25
    Qu
    -23.88
    (qu
    -23.00
    qa
    -23.00
     Qu
    -22.63
     q
    -22.50
    cq
    -22.50
    -qu
    -22.50
    SQ
    -22.38
    POSITIVE LOGITS
     Ames
    18.63
    ades
    16.13
    aden
    16.00
    ДЕ
    16.00
    ither
    15.75
     Tucson
    15.38
    ksz
    15.38
     Dayton
    14.69
     Ur
    14.56
    ivers
    14.44
    Activations Density 0.588%

    No Known Activations