© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8651
    Prev
    Next
    INDEX
    Explanations

    that clause

    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
    æĺ¯çľŁçļĦ
    -0.10
    à¸Ĭะ
    -0.09
    æ¿Ģ
    -0.09
    çĭ¬çī¹çļĦ
    -0.09
    åºļ
    -0.09
    /OR
    -0.09
     Orlando
    -0.09
    岿
    -0.09
    éĴı
    -0.08
    亲èĩª
    -0.08
    POSITIVE LOGITS
    æĺİçŁ¥
    0.11
    ä¸įæĩĤ
    0.11
    ä¸įäºĨ解
    0.11
    $$$$
    0.10
    并ä¸į代表
    0.09
    ä¸įä¸Ģå®ļ
    0.09
    æĹ©å·²
    0.09
    opy
    0.09
     knowing
    0.08
    注å®ļ
    0.08
    Activations Density 0.166%

    No Known Activations