© 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. 1048
    Prev
    Next
    INDEX
    Explanations

    say communication

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    atum
    -17.38
    FileSync
    -17.13
    hti
    -16.88
    card
    -16.63
    getToken
    -16.50
    aths
    -16.38
    маг
    -16.25
     tokenize
    -16.13
    证券交易
    -16.13
    魔术
    -15.94
    POSITIVE LOGITS
     shotgun
    19.25
    沟通
    18.13
     legal
    18.13
     Legal
    18.00
    Legal
    17.63
     communication
    16.88
     legally
    16.25
    communications
    15.94
     Jenner
    15.94
    communication
    15.63
    Activations Density 0.012%

    No Known Activations