© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    say "moral"

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

    No Comments

    Negative Logits
    .cap
    -18.38
     quant
    -18.38
    chef
    -18.25
    资本
    -17.75
     cookbook
    -17.63
    量化
    -17.63
    eat
    -17.00
     Quant
    -16.88
     ener
    -16.88
     cook
    -16.75
    POSITIVE LOGITS
    德育
    31.63
    道德
    29.88
     morality
    27.00
    Mor
    25.38
     Moral
    24.63
     moral
    24.38
     Mor
    23.88
     MOR
    23.00
    mor
    22.38
     mor
    20.88
    Activations Density 0.063%

    No Known Activations