© 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. 14401
    Prev
    Next
    INDEX
    Explanations

    say "scr"

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

    No Comments

    Negative Logits
     bail
    -21.25
     Farrell
    -21.00
     Gall
    -21.00
    达尔
    -20.38
    uart
    -20.25
    bast
    -20.25
    STALL
    -19.50
     uart
    -19.50
     tart
    -19.13
    dal
    -19.13
    POSITIVE LOGITS
    scr
    19.50
    SCR
    19.25
    _scr
    19.13
    pq
    18.00
     Scr
    17.63
    chr
    17.38
     Dre
    17.25
    斯基
    17.00
    _chr
    17.00
    Scr
    16.88
    Activations Density 1.285%

    No Known Activations