© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    say "application"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Cobb
    -14.94
    AVA
    -14.75
    uffix
    -14.69
    IVAL
    -14.38
    umph
    -14.38
    ềm
    -14.19
    道
    -14.13
    몰
    -13.81
    荣誉称号
    -13.56
    客人
    -13.50
    POSITIVE LOGITS
     application
    89.50
    应用
    82.00
    application
    80.50
     Application
    77.50
    Application
    75.50
    (application
    72.00
    .application
    69.00
     applications
    68.50
    _application
    68.50
    應用
    67.00
    Activations Density 0.468%

    No Known Activations