© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    [context] => [next word]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    layer
    -20.13
     layer
    -19.25
    $value
    -17.38
     layers
    -16.88
    	layer
    -16.00
    value
    -15.88
     value
    -15.50
    layers
    -15.38
    (layer
    -15.00
    $key
    -14.63
    POSITIVE LOGITS
     Equation
    18.00
    ...↵↵↵
    17.75
     Education
    16.88
     Output
    16.63
    Education
    16.13
     Structure
    16.13
     Area
    15.75
    imity
    15.69
     File
    15.63
     Scene
    15.63
    Activations Density 0.011%

    No Known Activations