© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14383
    Prev
    Next
    INDEX
    Explanations

    say "numbers"

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

    No Comments

    Negative Logits
    沉
    -18.00
    lify
    -17.38
    oka
    -17.00
    ("("
    -16.75
    (using
    -16.50
    (cl
    -15.81
    (xi
    -15.56
    麒麟
    -15.38
    aska
    -15.13
    нал
    -15.00
    POSITIVE LOGITS
     admission
    14.81
     Positioned
    14.25
    -sh
    13.63
    .getService
    13.31
    ................................
    13.31
    排行榜
    13.25
    _SHARED
    13.19
     evaluated
    13.19
    stdClass
    13.06
     exposures
    13.00
    Activations Density 0.048%

    No Known Activations