© 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. 57054
    Prev
    Next
    INDEX
    Explanations

    co-founded or who

    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
    çªģ
    -0.09
    æıª
    -0.08
    brush
    -0.08
    èªł
    -0.08
    è¿Ļä¸Ģ次
    -0.08
    mpl
    -0.08
    èĤ¯
    -0.08
    è¯ļ
    -0.08
     roy
    -0.07
    åīįæĸ¹
    -0.07
    POSITIVE LOGITS
    æĭħä»»
    0.14
    主æĮģ
    0.12
    ç¼ĸåĨĻ
    0.12
    æĵĶ
    0.12
    æĭħ
    0.12
    æݥ管
    0.11
    主ç¼ĸ
    0.11
    æİ¥æīĭ
    0.11
    亲èĩª
    0.11
    çīµå¤´
    0.10
    Activations Density 0.156%

    No Known Activations