© 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. 15740
    Prev
    Next
    INDEX
    Explanations

    say pr

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

    No Comments

    Negative Logits
    quer
    -27.00
     Quentin
    -22.13
     qw
    -22.13
    quent
    -21.50
    quir
    -20.63
    qw
    -20.38
    quil
    -19.63
     qq
    -19.63
    ques
    -19.25
    qué
    -19.13
    POSITIVE LOGITS
    _Pr
    17.00
    プレ
    16.63
    .pr
    16.50
    プリ
    16.38
     Circle
    16.25
    (ci
    15.88
    馆
    15.81
     Pr
    15.81
    Pr
    15.75
    .ball
    15.56
    Activations Density 0.679%

    No Known Activations