© 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. 8330
    Prev
    Next
    INDEX
    Explanations

    personal well-being and relationships

    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
    åıªä¼ļ
    -0.09
    为ä¾ĭ
    -0.09
    æį®æѤ
    -0.09
    两年åīį
    -0.08
    adem
    -0.08
    è¦ģ说
    -0.08
    ä¸įäºĪ
    -0.08
    oit
    -0.08
    ç©Ĺ
    -0.08
    éľĩæĥĬ
    -0.08
    POSITIVE LOGITS
    antt
    0.09
    æĮīæŶ
    0.09
    åį¯
    0.09
    æĤłéĹ²
    0.08
     <<=
    0.08
    åĩĨæŶ
    0.08
    ä¸Ģå¿ĥ
    0.08
    饯
    0.08
    cord
    0.08
    æ¯ı天
    0.08
    Activations Density 0.342%

    No Known Activations