© 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. 40111
    Prev
    Next
    INDEX
    Explanations

    professor, instructor, teaching, course, education

    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
    è¹ĩ
    -0.10
    æĹ©æĹ¥
    -0.10
    鼩
    -0.10
    å°±åĮ»
    -0.10
    erval
    -0.09
    ä¸ŃèĢĥ
    -0.09
    èĩªçĦ¶èĢĮ
    -0.09
    èĩªåıij
    -0.09
    .gdx
    -0.09
    rado
    -0.09
    POSITIVE LOGITS
    æķĻæİĪ
    0.15
     professor
    0.12
     пÑĢеп
    0.12
    Professor
    0.11
    æİĪ课
    0.11
     Professor
    0.11
    æķĻåѦ
    0.10
    (course
    0.10
     teaching
    0.10
     professors
    0.10
    Activations Density 0.120%

    No Known Activations