© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16285
    Prev
    Next
    INDEX
    Explanations

    say "communism"

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

    No Comments

    Negative Logits
     Masc
    -19.63
     Vet
    -17.88
    Closure
    -16.88
    窗口
    -16.50
    抵挡
    -15.88
     cavalry
    -15.69
     addslashes
    -15.50
     cursos
    -15.38
    estre
    -15.38
     stealth
    -15.38
    POSITIVE LOGITS
     Flat
    19.38
    Flat
    19.38
    平
    19.25
    和平
    18.88
     communal
    18.13
    utan
    17.88
    -flat
    17.75
    flat
    17.50
    百合
    17.38
     communism
    16.88
    Activations Density 0.251%

    No Known Activations