© 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. 15704
    Prev
    Next
    INDEX
    Explanations

    say cognition

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

    No Comments

    Negative Logits
    劫
    -18.63
    ropy
    -17.00
    _API
    -16.38
    API
    -16.25
    选股
    -16.13
    纛
    -16.00
    抗生素
    -15.88
    ��
    -15.81
    _decor
    -15.81
    吉祥
    -15.63
    POSITIVE LOGITS
    认知
    24.00
    认识
    21.38
    的认识
    19.75
    的认知
    18.75
    erea
    17.75
    感受
    17.00
    清醒
    16.88
    认识到
    16.88
     unaware
    16.63
    理解和
    16.50
    Activations Density 0.183%

    No Known Activations