© 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. 2124
    Prev
    Next
    INDEX
    Explanations

    say "ethical"

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

    No Comments

    Negative Logits
     play
    -24.25
    (play
    -22.50
     Play
    -22.50
    plays
    -22.00
    Play
    -21.88
    	play
    -20.13
     plays
    -20.00
    play
    -19.63
     played
    -19.38
    _play
    -18.88
    POSITIVE LOGITS
     ethical
    24.38
    道德
    23.75
    ethical
    19.88
    books
    17.25
     ethics
    16.38
    iad
    16.25
     Ethics
    16.00
     educational
    15.56
     moral
    15.44
    伦理
    15.44
    Activations Density 0.018%

    No Known Activations