© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14240
    Prev
    Next
    INDEX
    Explanations

    say "application"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    税费
    -16.25
    没收
    -14.75
    ogie
    -14.50
    损失
    -14.19
     Neptune
    -13.94
    税
    -13.94
    悦
    -13.75
    yte
    -13.69
     hostages
    -13.69
    damage
    -13.56
    POSITIVE LOGITS
     application
    88.50
    应用
    87.50
     applications
    84.50
     Application
    81.50
    Application
    78.50
    application
    78.00
     Applications
    75.50
    的应用
    75.50
    _application
    74.50
    applications
    74.50
    Activations Density 4.051%

    No Known Activations