© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14952
    Prev
    Next
    INDEX
    Explanations

    say "ran"

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

    No Comments

    Negative Logits
     Sting
    -24.38
    vig
    -22.75
     cig
    -22.13
     Jub
    -19.88
     Huff
    -19.75
     JFK
    -19.00
    udging
    -19.00
     Zig
    -19.00
     Ста
    -18.88
     Nev
    -18.75
    POSITIVE LOGITS
    兰
    27.25
    iran
    23.25
    蘭
    22.75
    Fran
    20.88
    兰花
    20.38
     Fran
    19.63
     Bans
    19.25
    ran
    19.25
     fran
    19.00
     Franz
    18.88
    Activations Density 1.052%

    No Known Activations