© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58117
    Prev
    Next
    INDEX
    Explanations

    disability and disabled people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adera
    -0.07
    éļĶå¤ľ
    -0.07
    estion
    -0.07
    庶
    -0.07
    NST
    -0.07
    å±Ĥ
    -0.06
    æĸĽ
    -0.06
    ród
    -0.06
    å¤ľ
    -0.06
    usercontent
    -0.06
    POSITIVE LOGITS
     disabilities
    0.16
    æ®ĭçĸ¾
    0.16
     disability
    0.15
     disabled
    0.13
    æ®ĭçĸ¾äºº
    0.13
     wheelchair
    0.13
     Disabilities
    0.13
     инвали
    0.12
     Disability
    0.12
    æĹłéļľç¢į
    0.12
    Activations Density 0.167%

    No Known Activations