© 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. 2605
    Prev
    Next
    INDEX
    Explanations

    say mag

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

    No Comments

    Negative Logits
    eter
    -19.75
    (Util
    -17.63
    eti
    -17.38
    ETER
    -16.63
     Ger
    -16.63
    cons
    -16.25
     terminated
    -16.13
    (util
    -16.13
     ger
    -16.00
    etr
    -16.00
    POSITIVE LOGITS
     mag
    70.50
    Mag
    70.00
     Mag
    67.50
    mag
    64.00
    _mag
    60.75
    .mag
    59.50
    魔
    44.50
     MAG
    42.50
    _MAG
    42.25
     Magick
    41.50
    Activations Density 0.090%

    No Known Activations