© 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. 2051
    Prev
    Next
    INDEX
    Explanations

    say "erg"

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

    No Comments

    Negative Logits
     Cur
    -19.75
    _cur
    -19.25
    Cur
    -18.63
    _et
    -18.63
    cur
    -18.38
    定量
    -17.88
    etter
    -17.75
     cur
    -17.50
     Ev
    -17.00
    .cur
    -16.50
    POSITIVE LOGITS
    erg
    41.25
     Berg
    38.50
     Erg
    36.50
     erg
    34.25
     berg
    30.88
    berg
    27.25
     Marg
    23.13
     Verg
    22.25
     BER
    21.75
     merg
    21.50
    Activations Density 0.047%

    No Known Activations