© 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. 34893
    Prev
    Next
    INDEX
    Explanations

    religious titles and 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
     Cand
    -0.10
    æĸ°åįİ社
    -0.08
    ãģŀ
    -0.08
     Expedition
    -0.08
    æĦļ
    -0.08
    uels
    -0.08
     cân
    -0.08
    æĿ¥ä¸įåıĬ
    -0.08
    pector
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    POSITIVE LOGITS
     GPLv
    0.10
    马åħĭæĢĿ
    0.10
    ä»ĩ
    0.10
    æ·¼
    0.10
    -strokes
    0.10
    æĸ«
    0.10
    æĴ¤
    0.09
    é©¿
    0.09
    å¸ĪåħĦ
    0.09
    esco
    0.09
    Activations Density 0.011%

    No Known Activations