© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2072
    Prev
    Next
    INDEX
    Explanations

    say "accented characters"

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

    No Comments

    Negative Logits
    珠江
    -17.75
    株洲
    -17.38
    (ref
    -16.63
    温
    -16.63
    位
    -16.25
    (src
    -16.13
     —↵↵
    -15.81
    ref
    -15.63
    achs
    -15.63
     src
    -15.44
    POSITIVE LOGITS
     �
    55.00
    Ā
    36.25
    ā
    33.75
    Ē
    33.50
     �
    31.13
    Ć
    29.63
    Ģ
    29.00
    ē
    29.00
    Ī
    28.63
    27.25
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.