© 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. 2091
    Prev
    Next
    INDEX
    Explanations

    say "extr"

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

    No Comments

    Negative Logits
     perms
    -19.75
     perm
    -18.50
    Mag
    -18.13
     nums
    -18.00
    nums
    -17.88
    perms
    -17.88
    perm
    -17.75
    _permissions
    -17.50
    -export
    -16.88
     magnitude
    -16.00
    POSITIVE LOGITS
     extr
    50.50
     Extr
    44.50
    extr
    40.25
     estr
    24.63
     ext
    23.88
     str
    20.13
    hex
    19.75
     hex
    19.50
     extract
    19.00
    (str
    18.50
    Activations Density 0.052%

    No Known Activations