© 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. 33302
    Prev
    Next
    INDEX
    Explanations

    disease and health conditions

    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
    é«ĺãģĦ
    -0.09
    ession
    -0.09
    pgsql
    -0.09
    phasis
    -0.09
    HEL
    -0.08
    ìĬ¤íģ¬
    -0.08
     Aquarium
    -0.08
    溯
    -0.08
    tsy
    -0.08
    å¸ĥæľĹ
    -0.08
    POSITIVE LOGITS
    çĸ¾çĹħ
    0.12
    çĹħ
    0.12
    æĢ§çĸ¾çĹħ
    0.11
     disease
    0.10
    çĸ¾çĹħçļĦ
    0.10
    çĹħçĹĩ
    0.10
    Hur
    0.09
     diseases
    0.09
    çĶŁçĹħ
    0.09
     заболеваниÑı
    0.09
    Activations Density 0.899%

    No Known Activations