© 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. 14453
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
     Kane
    -19.38
    坛
    -19.25
    iete
    -19.25
    okit
    -18.63
    irc
    -17.88
    愔
    -17.25
     Olympia
    -17.25
    itary
    -17.13
    ROME
    -17.13
    (dc
    -17.00
    POSITIVE LOGITS
     Craw
    17.38
    蹭
    16.88
    ren
    14.56
    皴
    14.56
     Tam
    13.94
     shred
    13.88
     Howell
    13.25
    ら
    13.13
    撒
    12.56
     Chevron
    12.50
    Activations Density 0.051%

    No Known Activations