© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    born in places

    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
    омеÑĢ
    -0.09
    为æŃ¢
    -0.09
    åĪ°ä½į
    -0.09
    ies
    -0.09
    adesh
    -0.08
    轩
    -0.08
    çļĦåģļæ³ķ
    -0.08
    为代表
    -0.08
     pains
    -0.08
    åĮºç®¡å§Ķä¼ļ
    -0.08
    POSITIVE LOGITS
    çĶŁãģ¾ãĤĮ
    0.11
    ä»İå°ıå°±
    0.11
    ä»İå°ı
    0.11
    åĩºèº«
    0.11
    åĩºçĶŁ
    0.11
    çĶŁäºİ
    0.10
    åĩºçĶŁäºİ
    0.10
    æĺ¯ä¸ĢåIJį
    0.09
     born
    0.09
     водо
    0.09
    Activations Density 0.202%

    No Known Activations