© 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. 2571
    Prev
    Next
    INDEX
    Explanations

    say Greek numeral prefixes

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

    No Comments

    Negative Logits
     Marg
    -16.75
    EMU
    -15.19
    Marg
    -14.00
    xAE
    -13.81
    _EOF
    -13.75
    ERM
    -13.75
     coron
    -13.56
     capitalized
    -13.06
     margins
    -13.06
    Phil
    -13.06
    POSITIVE LOGITS
     tet
    87.50
     Tet
    81.50
    tet
    75.00
     hex
    54.00
    Hex
    49.25
     oct
    48.75
     Hex
    48.50
    hex
    47.50
    quad
    46.75
    (hex
    46.00
    Activations Density 0.038%

    No Known Activations