© 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. 15808
    Prev
    Next
    INDEX
    Explanations

    say "truth"

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

    No Comments

    Negative Logits
    资源
    -17.13
    痉
    -17.00
    符号
    -16.25
    机电
    -16.13
    sgi
    -16.00
     IMS
    -15.94
    兼职
    -15.94
     symb
    -15.63
     Riley
    -15.56
    核心区
    -15.38
    POSITIVE LOGITS
    Truth
    29.38
     Truth
    28.75
     truth
    28.25
    truth
    27.38
    真理
    24.75
    真相
    24.25
     truths
    23.88
     truthful
    23.50
    _truth
    22.75
     honesty
    21.38
    Activations Density 0.204%

    No Known Activations