© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1406
    Prev
    Next
    INDEX
    Explanations

    [Soviet] => [Soviet]

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

    No Comments

    Negative Logits
    政治
    -20.25
     communism
    -19.63
    CCI
    -19.13
     comput
    -18.75
     USSR
    -18.38
     Communist
    -18.25
     TOK
    -18.00
     Soviet
    -17.88
     politics
    -17.63
     political
    -17.38
    POSITIVE LOGITS
     energy
    16.75
    games
    15.88
    ť
    15.75
    エネルギー
    15.13
     Palace
    15.13
    bones
    15.00
    能量
    14.88
    骨
    14.75
    erson
    14.56
     bones
    14.50
    Activations Density 0.133%

    No Known Activations