© 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. 3112
    Prev
    Next
    INDEX
    Explanations

    say investment

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    領域
    -20.75
    领域
    -19.75
    systems
    -19.00
    领域的
    -18.63
    系统的
    -18.00
    样子
    -17.63
     system
    -17.50
     page
    -17.50
    字段
    -17.13
    system
    -17.00
    POSITIVE LOGITS
     investment
    29.13
    投资
    27.50
     Investment
    26.50
    investment
    25.63
     input
    24.38
    输入
    21.88
    (input
    21.38
    input
    21.00
     Input
    20.63
     installation
    20.13
    Activations Density 0.058%

    No Known Activations