© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    say "endpoint"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     board
    -22.50
    board
    -21.13
    _board
    -21.00
    (board
    -20.13
    Board
    -19.63
     boards
    -18.50
     Board
    -17.88
     Boards
    -17.75
    板
    -17.50
    boards
    -17.25
    POSITIVE LOGITS
     endpoint
    56.25
    endpoint
    51.00
    Endpoint
    47.00
     Endpoint
    46.75
    (endpoint
    43.25
    _endpoint
    41.75
    .endpoint
    40.50
     endpoints
    40.00
     route
    36.50
     Route
    32.25
    Activations Density 0.040%

    No Known Activations