© 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. 36730
    Prev
    Next
    INDEX
    Explanations

    holistic, comprehensive, complete, overall

    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
    èħ¾
    -0.10
    æī¼
    -0.09
    åī½
    -0.09
    ucci
    -0.08
    alon
    -0.08
    åĸ§
    -0.08
    éij
    -0.08
    éģĴ
    -0.08
    æĪ´
    -0.08
    è¿Ļ两ç§į
    -0.08
    POSITIVE LOGITS
    综åIJĪæĢ§
    0.18
    æķ´ä½ĵ
    0.15
    èĢĮéĿŀ
    0.14
    çļĦæķ´ä½ĵ
    0.13
    èĢĮä¸įæĺ¯
    0.13
    æķ´ä¸ªäºº
    0.12
    综åIJĪ
    0.12
    åĮħæĭ¬
    0.12
     rather
    0.12
    æķ´ä¸ª
    0.11
    Activations Density 0.119%

    No Known Activations