© 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. 20636
    Prev
    Next
    INDEX
    Explanations

    writing about programming and rights

    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
     ÑĢеÑĪи
    -0.09
    пÑĢе
    -0.08
    æ²Ķ
    -0.08
    .Inject
    -0.08
    ÑģÑı
    -0.08
    prite
    -0.08
     ÙĦدÙĬ
    -0.08
    ì°½
    -0.08
    еннаÑı
    -0.08
     ÑģÑĤоимоÑģÑĤи
    -0.08
    POSITIVE LOGITS
    fos
    0.10
    è¿Ļæīįæĺ¯
    0.10
    ees
    0.10
    太å¤ļçļĦ
    0.10
    éģ´
    0.09
    aires
    0.09
    owl
    0.09
    æľĢå¤ļçļĦ
    0.09
    å½ĵä¹ĭ
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    Activations Density 1.388%

    No Known Activations