© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1884
    Prev
    Next
    INDEX
    Explanations

    [marine] => [marine]

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

    No Comments

    Negative Logits
     marine
    -37.50
     Marine
    -36.50
     MAR
    -31.13
     Martian
    -30.13
     Marines
    -29.13
     Mart
    -27.38
     mart
    -27.38
     Mars
    -27.13
     Marie
    -27.00
    marine
    -27.00
    POSITIVE LOGITS
    钙
    16.38
     INTERFACE
    16.13
    rice
    16.00
    酢
    15.38
    yi
    14.94
    醋
    14.94
     Telescope
    14.94
    /sw
    14.63
     photographers
    14.50
     hair
    14.44
    Activations Density 0.103%

    No Known Activations