© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3267
    Prev
    Next
    INDEX
    Explanations

    say site

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     address
    -19.38
    Address
    -18.88
     trucks
    -18.75
    强奸
    -18.38
    driver
    -18.38
    /address
    -18.13
    truck
    -17.75
     Address
    -17.75
    地址
    -17.63
     drivers
    -17.25
    POSITIVE LOGITS
    (site
    24.00
     SITE
    23.75
    _SITE
    21.50
    .site
    21.38
     site
    20.88
    _site
    20.00
    Site
    19.75
    .Site
    19.75
    site
    19.63
    -site
    19.38
    Activations Density 0.014%

    No Known Activations