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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2440
    Prev
    Next
    INDEX
    Explanations

    say ethics

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

    No Comments

    Negative Logits
    定
    -28.88
    (det
    -24.63
    det
    -23.63
    Det
    -23.00
     det
    -22.25
     Det
    -21.50
     DET
    -21.25
    -det
    -20.88
     determin
    -20.63
     determinant
    -20.25
    POSITIVE LOGITS
    伦理
    24.38
    保守
    18.75
    _PROTOCOL
    17.75
    prot
    17.63
    _protocol
    17.38
    Mor
    17.13
     recursion
    16.63
     Consent
    16.63
    Eth
    16.38
    .Protocol
    16.25
    Activations Density 0.178%

    No Known Activations