© 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. 2533
    Prev
    Next
    INDEX
    Explanations

    say "Jan"

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

    No Comments

    Negative Logits
    	dst
    -18.25
     dst
    -17.63
    capital
    -17.50
    orra
    -16.88
    digest
    -16.00
    eworld
    -16.00
    utow
    -15.69
     capsule
    -15.38
    Capital
    -15.38
    atter
    -15.19
    POSITIVE LOGITS
     Jan
    51.50
    Jan
    49.25
     Oct
    35.00
     Feb
    34.25
     tet
    33.75
     Tet
    33.00
     jan
    31.50
     JAN
    31.50
    Oct
    31.38
     quad
    29.00
    Activations Density 0.073%

    No Known Activations