© 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. 56933
    Prev
    Next
    INDEX
    Explanations

    religious or organizational terms

    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
     اÙĦÙħÙĦ
    -0.10
    é¦Ķ
    -0.10
    ridge
    -0.10
    æĺĨ
    -0.09
    gary
    -0.09
    家éĩĮ
    -0.09
    æīĵæī®
    -0.09
    é¢
    -0.09
    pts
    -0.09
    geist
    -0.08
    POSITIVE LOGITS
    秩
    0.10
    sWith
    0.10
    ино
    0.09
    ental
    0.09
    ulla
    0.09
    uales
    0.09
    avern
    0.09
    ional
    0.09
    éĤĵå°ı
    0.09
    onal
    0.09
    Activations Density 0.002%

    No Known Activations