© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    say "reaction"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     plumbing
    -17.63
     Visitor
    -17.50
     plum
    -17.50
    lick
    -17.25
    霏
    -17.13
     poop
    -17.13
     bidder
    -16.88
    メーカー
    -16.88
     hauling
    -16.88
     searcher
    -16.75
    POSITIVE LOGITS
     reaction
    17.88
     Mits
    16.63
    bz
    16.13
     Reaction
    15.88
    .weixin
    15.88
     masked
    15.50
     reactions
    14.94
    PRODUCT
    14.75
     Plan
    14.44
    masked
    14.44
    Activations Density 0.101%

    No Known Activations