© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27700
    Prev
    Next
    INDEX
    Explanations

    paralympics or disability classifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æıª
    -0.09
    åī¥ç¦»
    -0.09
    æī°
    -0.09
    ä¿Ŀ驾
    -0.09
     pearl
    -0.09
    วà¸ĩ
    -0.09
    çıįçıł
    -0.08
    nest
    -0.08
     fray
    -0.08
    æ´¾åĩºæīĢ
    -0.08
    POSITIVE LOGITS
    æ®ĭçĸ¾
    0.19
    æ®ĭçĸ¾äºº
    0.18
     wheelchair
    0.18
    æĭĦ
    0.15
     disabilities
    0.14
     disability
    0.14
    èĨij
    0.13
    åıĮèħ¿
    0.13
     cripp
    0.13
    æĹłéļľç¢į
    0.12
    Activations Density 0.144%

    No Known Activations