© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    say "俄国"

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

    No Comments

    Negative Logits
    det
    -19.13
    facility
    -18.75
    fac
    -18.25
    校
    -17.88
    Dem
    -17.88
    Fac
    -17.63
     DEM
    -17.50
    Leg
    -17.25
    ter
    -17.25
     facets
    -17.13
    POSITIVE LOGITS
    俄国
    33.00
    乙
    26.63
    甲
    25.38
    俄
    25.00
    (ret
    24.50
    meth
    23.63
     Meth
    23.13
    -ret
    22.38
     ret
    22.00
     Ret
    21.25
    Activations Density 0.030%

    No Known Activations