© 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. 15312
    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
    ymax
    -24.63
    inery
    -23.63
    azon
    -23.13
    kid
    -21.50
    pai
    -20.13
    kad
    -20.13
    iado
    -20.13
    ypad
    -20.00
     lineno
    -19.88
    hiba
    -19.75
    POSITIVE LOGITS
    RE
    19.25
    re
    16.38
    Re
    15.44
    -re
    15.00
    _re
    14.88
    ren
    14.50
    tls
    14.44
     re
    14.00
    G
    13.56
    勃
    13.38
    Activations Density 0.014%

    No Known Activations