© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    disability and disabilities

    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
    est
    -0.11
    ãģ¤ãĤĤãĤĬ
    -0.11
    禺
    -0.10
    çŁ³æ¦´
    -0.09
    äºĨ大éĩıçļĦ
    -0.09
    uild
    -0.09
    icles
    -0.09
    hält
    -0.09
    -up
    -0.09
    inals
    -0.09
    POSITIVE LOGITS
    areth
    0.09
    aire
    0.08
    gesch
    0.08
    indent
    0.08
    ÑĤив
    0.08
    çķĮçļĦ
    0.08
    çķĮ
    0.08
    ä¸Ģ线
    0.08
     اÙĦعاÙħØ©
    0.08
    ìľ¤
    0.08
    Activations Density 0.009%

    No Known Activations