© 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. 2819
    Prev
    Next
    INDEX
    Explanations

    say morality

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

    No Comments

    Negative Logits
     mill
    -18.63
     millis
    -17.25
    /chart
    -17.00
    curr
    -16.25
     curr
    -16.25
    chron
    -15.63
    perm
    -15.56
    mill
    -15.25
    .curr
    -15.13
    endent
    -15.06
    POSITIVE LOGITS
    道德
    58.50
     morality
    42.00
    伦理
    39.00
     ethics
    38.75
     Mor
    37.75
     ethical
    37.25
     moral
    37.00
     Ethics
    36.50
    Mor
    36.00
     Moral
    35.50
    Activations Density 0.070%

    No Known Activations