© 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. 57472
    Prev
    Next
    INDEX
    Explanations

    software project 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
    edb
    -0.08
    å¼ĢåĬŀ
    -0.08
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.08
    该åİ¿
    -0.08
    æĮº
    -0.08
    ht
    -0.08
    大桥
    -0.08
    ãĥĶãĥ¼
    -0.08
    æĮīè§Ħå®ļ
    -0.08
    aul
    -0.08
    POSITIVE LOGITS
    .org
    0.10
    榨
    0.10
    URT
    0.09
    ä¸Ńæĸĩ
    0.09
    æĨĭ
    0.09
    \CMS
    0.09
    å·¦æīĭ
    0.09
    榷
    0.09
     Nachricht
    0.09
     mailing
    0.09
    Activations Density 0.651%

    No Known Activations