© 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. 14124
    Prev
    Next
    INDEX
    Explanations

    say adaptations

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

    No Comments

    Negative Logits
     addAction
    -20.13
    (Action
    -16.88
    -action
    -16.75
    CLS
    -16.63
    (action
    -16.63
     ACTION
    -16.50
    黩
    -16.50
     action
    -16.25
    .addAction
    -16.00
    坐标
    -16.00
    POSITIVE LOGITS
     adaptations
    20.88
     adaptation
    17.63
     BitmapFactory
    16.00
     structures
    15.94
     efficiencies
    15.81
     evolved
    15.81
    mars
    15.81
     Efficiency
    15.69
     efficiency
    15.56
    ev
    15.50
    Activations Density 0.355%

    No Known Activations