© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16274
    Prev
    Next
    INDEX
    Explanations

    say "Greek letters"

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

    No Comments

    Negative Logits
    /q
    -22.13
    qc
    -21.88
    /qu
    -21.75
    .qu
    -21.38
    qp
    -20.50
    .Qu
    -20.25
    qd
    -20.25
    阙
    -20.13
    Queen
    -20.13
     Qu
    -20.13
    POSITIVE LOGITS
    胡萝卜
    22.25
     PSI
    20.75
    _pwm
    20.75
    eltas
    20.63
    elli
    19.25
     gamma
    19.00
    免疫
    18.88
    sigma
    18.75
     bcrypt
    18.63
    _PWM
    18.63
    Activations Density 0.841%

    No Known Activations