© 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. 15753
    Prev
    Next
    INDEX
    Explanations

    say disability terms

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

    No Comments

    Negative Logits
    沱
    -21.00
    anche
    -17.75
     poison
    -16.25
    eton
    -16.25
    ufacturer
    -16.00
    农药
    -15.75
     agr
    -15.69
     pll
    -15.69
    nodeValue
    -15.31
    zeros
    -15.06
    POSITIVE LOGITS
     disability
    26.63
     Disability
    26.50
     Disabilities
    25.63
    残疾人
    24.50
    残疾
    24.50
     disabled
    24.25
    无障碍
    24.00
     Accessibility
    23.75
     disabilities
    23.50
     Disabled
    23.13
    Activations Density 0.307%

    No Known Activations