© 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. 22988
    Prev
    Next
    INDEX
    Explanations

    ill health or illness

    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
    HeaderCode
    -0.09
    çĢijå¸ĥ
    -0.09
    beeld
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    pei
    -0.08
    RGBO
    -0.08
    /place
    -0.08
    纶
    -0.08
    adier
    -0.08
    неÑģен
    -0.08
    POSITIVE LOGITS
     ill
    0.11
    æĬĬæı¡
    0.10
    ly
    0.10
    ness
    0.10
     Ill
    0.09
    fully
    0.09
    rary
    0.08
    itude
    0.08
    itudes
    0.08
    upy
    0.08
    Activations Density 0.150%

    No Known Activations