© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    instance

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     David
    -17.38
    道
    -16.75
    obutton
    -16.63
    rin
    -15.75
    David
    -15.69
    ipi
    -15.25
    门
    -15.00
    方向
    -14.63
    的城市
    -14.56
    門
    -14.50
    POSITIVE LOGITS
     instance
    61.75
    instance
    61.75
     Instance
    57.00
    Instance
    56.25
    	instance
    52.50
    _instance
    52.00
    .instance
    52.00
    (instance
    51.25
    -instance
    45.75
     instances
    43.50
    Activations Density 0.083%

    No Known Activations