© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50500
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
     Slee
    -0.09
    大大
    -0.08
     sleeves
    -0.08
     оÑĤд
    -0.08
    hydr
    -0.08
     Rap
    -0.08
    acy
    -0.08
    æ£ķ
    -0.08
    iston
    -0.08
    æīĭä¸ŃçļĦ
    -0.08
    POSITIVE LOGITS
    åīįè¡Į
    0.10
    讲课
    0.10
    æIJŀå®ļ
    0.09
    å´ĩ
    0.09
     اÙĦÙĪصÙĪÙĦ
    0.09
    tos
    0.09
    è¿ĺç®Ĺ
    0.09
    æĢ¥äºİ
    0.09
    éĢĥéģ¿
    0.09
     hạ
    0.09
    Activations Density 0.159%

    No Known Activations