© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15461
    Prev
    Next
    INDEX
    Explanations

    say "Gurmukhi letters"

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

    No Comments

    Negative Logits
    衣柜
    -21.75
     Abram
    -20.50
    adin
    -20.50
    Kay
    -20.25
     Kay
    -20.13
     Salem
    -20.13
    柜
    -20.00
     Calvin
    -19.38
    rail
    -19.25
    槐
    -19.13
    POSITIVE LOGITS
    pong
    31.88
    OND
    28.13
    ond
    27.88
    onta
    27.75
    conc
    27.38
     pong
    27.25
     Christie
    27.13
     Conc
    25.88
    ong
    24.88
     conc
    24.63
    Activations Density 6.775%

    No Known Activations