© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    say request

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     field
    -19.25
    -field
    -17.63
    field
    -17.50
     column
    -16.38
    (field
    -16.13
     angle
    -15.88
     Angle
    -15.56
    (column
    -15.50
     Field
    -15.38
    _Field
    -15.38
    POSITIVE LOGITS
     request
    64.50
    request
    61.00
    请求
    54.50
    Request
    52.75
    _request
    52.00
     Request
    51.25
    	request
    50.50
    .request
    47.25
    -request
    45.75
    :request
    45.75
    Activations Density 0.144%

    No Known Activations