© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    [year] => [day]

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

    No Comments

    Negative Logits
    itorio
    -21.38
    ystore
    -20.13
    inery
    -18.75
    lsi
    -18.75
    asley
    -17.63
    HashCode
    -17.38
    aways
    -17.38
    神仙
    -17.13
    yny
    -17.00
    slack
    -17.00
    POSITIVE LOGITS
    澳门
    16.88
    ogn
    15.75
    át
    14.25
     Mö
    13.88
     downt
    13.88
     Dunk
    13.75
     Budd
    13.75
    upt
    13.69
    üss
    13.56
     vest
    13.50
    Activations Density 0.110%

    No Known Activations