© 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. 20728
    Prev
    Next
    INDEX
    Explanations

    faculty and academic positions

    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
    æĮĩæĮ¥éĥ¨
    -0.11
    .shtml
    -0.10
    dio
    -0.10
    æĦıä¹īä¸Ĭ
    -0.10
    SED
    -0.09
    -buffer
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    大å±Ģ
    -0.09
    è¡į
    -0.09
    éĢŁåº¦å¿«
    -0.08
    POSITIVE LOGITS
    å¸ĪèµĦ
    0.15
     faculty
    0.11
    æķĻèģĮå·¥
    0.11
     teaching
    0.11
    ä¸ĵèģĮ
    0.10
     teachers
    0.10
    æī§æķĻ
    0.10
    èģĮå·¥
    0.10
    æķĻå¸Ī
    0.10
     staff
    0.10
    Activations Density 0.076%

    No Known Activations