© 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. 16310
    Prev
    Next
    INDEX
    Explanations

    say "freedom"

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

    No Comments

    Negative Logits
    埭
    -19.38
    戚
    -17.63
    沓
    -17.25
    CEF
    -16.88
    beck
    -16.38
    .addClass
    -15.94
    黏
    -15.88
     dõi
    -15.75
     Kı
    -15.63
    inka
    -15.44
    POSITIVE LOGITS
    自由
    47.75
     freedom
    40.75
    Freedom
    39.75
     autonomy
    38.00
    自主
    37.25
     Freedom
    37.00
     liberté
    36.25
     자유
    35.75
     свобод
    35.75
     free
    35.50
    Activations Density 0.536%

    No Known Activations