© 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. 2792
    Prev
    Next
    INDEX
    Explanations

    say "mag" words

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

    No Comments

    Negative Logits
     tet
    -20.38
    (cur
    -20.38
    .cur
    -19.13
    tet
    -18.25
     cur
    -17.75
    乙方
    -17.63
     Tet
    -17.38
    (ret
    -17.38
    quad
    -17.13
    erm
    -16.75
    POSITIVE LOGITS
     magn
    52.25
     Magn
    50.25
    Magn
    44.00
     mag
    41.00
    Mag
    40.25
    mag
    39.00
    _mag
    38.75
     Mag
    37.50
    _MAG
    36.50
     magnitude
    35.75
    Activations Density 0.060%

    No Known Activations