© 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. 2286
    Prev
    Next
    INDEX
    Explanations

    say "per"

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

    No Comments

    Negative Logits
    facility
    -19.13
    感情
    -18.00
     facility
    -17.63
     Facility
    -17.50
    fac
    -17.00
    Fac
    -16.38
     Medal
    -16.25
     Mé
    -15.56
     Facilities
    -15.31
     Bordeaux
    -15.00
    POSITIVE LOGITS
    透
    70.00
     Per
    54.00
     perm
    52.75
    (per
    52.00
    Per
    52.00
    perm
    48.50
    Perm
    48.00
    -per
    47.75
    per
    45.00
     perms
    44.50
    Activations Density 0.037%

    No Known Activations