© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    say "accented" letters

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

    No Comments

    Negative Logits
     pres
    -25.75
     Pres
    -24.63
    -pres
    -22.50
     preservation
    -22.38
    Pres
    -22.00
    pres
    -21.50
    serial
    -20.00
     PRES
    -18.63
     preserving
    -18.63
     preserved
    -18.50
    POSITIVE LOGITS
    É
    40.50
     É
    39.00
     é
    36.75
     mé
    32.25
     Mé
    30.38
    é
    30.38
    mé
    26.88
    ér
    26.25
    gé
    24.75
     Ré
    23.63
    Activations Density 0.062%

    No Known Activations