© 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. 27785
    Prev
    Next
    INDEX
    Explanations

    Zen Buddhist temples, Tibetan names, Chinese names

    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
    èIJĮ
    -0.10
    åĮ£
    -0.09
    åĪ»
    -0.09
    èµĭ
    -0.09
    å°ı鸣
    -0.09
    çIJµ
    -0.09
    declar
    -0.09
    åIJı
    -0.09
    à´µ
    -0.08
    ampo
    -0.08
    POSITIVE LOGITS
    大å¸Ī
    0.09
    robe
    0.08
     Visitor
    0.08
    æ²Ļ滩
    0.08
    åIJįçīĩ
    0.08
    ä¼łæī¿
    0.08
    ovic
    0.08
    elli
    0.08
    æľīä¿¡å¿ĥ
    0.08
    æĸ°ä¸Ģ代
    0.08
    Activations Density 0.039%

    No Known Activations