© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35886
    Prev
    Next
    INDEX
    Explanations

    corticosteroid

    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
    éĺħ读åħ¨æĸĩ
    -0.11
    æĢħ
    -0.10
    éķ¿ä¸īè§Ĵ
    -0.09
    é¢ĨåĨĽ
    -0.09
    æĬī
    -0.09
     unc
    -0.09
    表述
    -0.09
    ç´į
    -0.09
    çıº
    -0.09
    extView
    -0.09
    POSITIVE LOGITS
     steroids
    0.11
     rein
    0.10
    fol
    0.08
    çIJ¥
    0.08
    stash
    0.08
     Schneider
    0.08
    ä¾Ŀ
    0.08
    orbit
    0.08
    è£ģ
    0.08
     cort
    0.08
    Activations Density 0.248%

    No Known Activations