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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15906
    Prev
    Next
    INDEX
    Explanations

    say agn

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

    No Comments

    Negative Logits
    .stamp
    -20.38
    stamp
    -19.75
    Stamp
    -18.75
    牛肉
    -18.63
     Stamp
    -18.00
    违法
    -17.88
    娼
    -17.25
    酬
    -16.88
     stamp
    -16.63
    carbon
    -16.50
    POSITIVE LOGITS
    .diag
    21.75
     диаг
    21.50
    诊断
    20.50
     diag
    20.25
    -di
    19.88
     DIAG
    19.88
    _diag
    19.75
    _DIAG
    19.63
     Di
    19.50
     diagnostics
    19.38
    Activations Density 0.612%

    No Known Activations