© 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. 47456
    Prev
    Next
    INDEX
    Explanations

    disabled people and accessibility

    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
    æ®ĭçĸ¾
    -0.16
    æ®ĭçĸ¾äºº
    -0.16
    èģĭ
    -0.15
    åĵij
    -0.15
    æĹłéļľç¢į
    -0.12
     disability
    -0.11
     handicap
    -0.11
    éļľ
    -0.11
    è§ĨåĬĽ
    -0.11
     Disability
    -0.11
    POSITIVE LOGITS
    æ¯ķ
    0.11
    NewProp
    0.10
    iske
    0.10
    èĺħ
    0.10
    etsk
    0.09
    PropertyParams
    0.09
    çķ¢
    0.09
    PFN
    0.09
    èł¹
    0.09
    æ¹į
    0.09
    Activations Density 0.075%

    No Known Activations