© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59200
    Prev
    Next
    INDEX
    Explanations

    disabilities and special needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    满
    -0.10
    涤
    -0.10
    èī¯å¿ĥ
    -0.10
    ä¼Ļ
    -0.09
    å½»
    -0.09
    å±¥
    -0.09
    iske
    -0.09
     кÑĢед
    -0.09
    åĭĺå¯Ł
    -0.09
    èį¼
    -0.08
    POSITIVE LOGITS
    æ®ĭçĸ¾äºº
    0.17
    æ®ĭçĸ¾
    0.15
     disabilities
    0.14
     disability
    0.13
    éļľ
    0.13
     disabled
    0.13
    èģĭ
    0.12
     Disabilities
    0.11
    Disabled
    0.11
    disabled
    0.11
    Activations Density 0.117%

    No Known Activations