© 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. 14260
    Prev
    Next
    INDEX
    Explanations

    say accented

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

    No Comments

    Negative Logits
    鹞
    -19.50
    海滩
    -18.25
     renters
    -17.88
    菜鸟
    -17.88
    kp
    -17.63
     Shack
    -17.63
    翅膀
    -17.38
    (thread
    -17.38
    驾车
    -17.38
    dbuf
    -17.25
    POSITIVE LOGITS
    �
    18.75
    ège
    16.50
     São
    15.81
     Colombian
    15.13
    gé
    14.94
    ós
    14.88
     mé
    13.94
     modèle
    13.88
     relación
    13.69
     relaciones
    13.63
    Activations Density 0.776%

    No Known Activations