© 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. 14782
    Prev
    Next
    INDEX
    Explanations

    say president

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    RIES
    -17.38
    iew
    -17.25
    uing
    -17.13
     Terraria
    -17.00
    矿区
    -16.50
    数据
    -16.38
    经济技术
    -16.38
     DataView
    -16.25
    數據
    -16.25
     filter
    -16.13
    POSITIVE LOGITS
    总统
    29.50
     presidency
    28.38
     presidents
    27.75
     presidential
    27.63
     Presidents
    26.13
    美国总统
    25.38
    President
    25.00
    白宫
    24.88
     President
    24.88
     Presidential
    24.75
    Activations Density 0.292%

    No Known Activations