© 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. 2711
    Prev
    Next
    INDEX
    Explanations

    say "ā"

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

    No Comments

    Negative Logits
    Reflect
    -18.50
     Reflect
    -18.38
    reflect
    -18.25
    ◻
    -17.75
     integr
    -17.38
    /fa
    -17.25
     reflect
    -17.00
    Mirror
    -16.63
    VER
    -16.00
    ver
    -15.19
    POSITIVE LOGITS
    ā
    39.00
    Ā
    36.75
     �
    33.75
    ū
    30.63
    Ī
    29.75
    ē
    29.25
    ī
    27.50
    Ō
    25.50
     �
    25.00
    ‐
    24.88
    Activations Density 0.083%

    No Known Activations