© 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. 37494
    Prev
    Next
    INDEX
    Explanations

    time after events

    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
    çļĦåŃ¦ä¹ł
    -0.09
     ÑģÑĥдеб
    -0.09
     обÑıзаÑĤелÑĮно
    -0.08
    ä¸Ģ段æŶéĹ´
    -0.08
    ForKey
    -0.08
     Kushner
    -0.08
    è¿Ļåĩłå¹´
    -0.08
    ä¸Ģ天
    -0.08
    aders
    -0.08
     Disqus
    -0.08
    POSITIVE LOGITS
    缸èģļ
    0.10
    -than
    0.10
    å½¼æѤ
    0.09
    åIJĮä¸Ģ个
    0.09
    æ£
    0.09
    kes
    0.09
    æ¶ī足
    0.08
    æľĢåĪĿçļĦ
    0.08
    /month
    0.08
    ARI
    0.08
    Activations Density 0.020%

    No Known Activations