© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60684
    Prev
    Next
    INDEX
    Explanations

    phase I/II clinical studies

    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
    Negative Logits
    ç»Łæ²»
    -0.10
    ecom
    -0.10
    éĻįèIJ½
    -0.09
    åį°è±¡
    -0.09
    è´¡çĮ®
    -0.09
    躺
    -0.08
    ainers
    -0.08
    ä»»ä½ķæŶåĢĻ
    -0.08
    jis
    -0.08
    Äĥng
    -0.08
    POSITIVE LOGITS
    åı¯è¡ĮæĢ§
    0.09
    åĪĿ次
    0.09
    ä¸Ńä»ĭæľºæŀĦ
    0.09
    åĪĿæŃ¥
    0.08
    第ä¸Ģ次
    0.08
    è¯ķçĤ¹
    0.08
    åīįæľŁ
    0.08
     manus
    0.08
    Bush
    0.08
    临åºĬ
    0.08
    Activations Density 0.165%

    No Known Activations