© 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. 14623
    Prev
    Next
    INDEX
    Explanations

    say "9"

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

    No Comments

    Negative Logits
    ede
    -17.88
    epend
    -15.38
    руд
    -15.25
    o
    -15.00
    imes
    -14.81
    illas
    -14.56
    ile
    -14.31
    umes
    -14.25
    os
    -14.19
    ables
    -14.06
    POSITIVE LOGITS
    游戏中
    17.63
    进球
    16.75
    哺
    16.50
    Authentication
    16.25
    AAF
    16.13
     Roulette
    16.13
    Javascript
    16.00
     Hosp
    15.81
    MJ
    15.69
    下沉
    15.69
    Activations Density 0.119%

    No Known Activations