© 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. 2510
    Prev
    Next
    INDEX
    Explanations

    say "lang"

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

    No Comments

    Negative Logits
    etr
    -19.50
     hexadecimal
    -18.13
     digit
    -16.63
    det
    -15.63
    aday
    -15.56
     det
    -15.50
    character
    -15.38
    etus
    -15.38
    数字
    -15.31
     mathematics
    -15.19
    POSITIVE LOGITS
     lang
    47.00
    Lang
    44.50
     Lang
    44.00
    lang
    43.50
    (lang
    42.00
    _lang
    38.25
    /lang
    36.50
    .lang
    36.25
    .Lang
    35.00
    -lang
    34.75
    Activations Density 0.027%

    No Known Activations