© 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. 22387
    Prev
    Next
    INDEX
    Explanations

    school and educational contexts

    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
    æĪIJ人
    -0.09
    ç¦ģ
    -0.09
    çłŃ
    -0.09
    æĪIJ年人
    -0.08
    马æĿ¥
    -0.08
    å¾Ģå¤ĸ
    -0.08
    .assertj
    -0.08
    èĪªæµ·
    -0.08
    åıijå±ķ空éĹ´
    -0.08
    oust
    -0.08
    POSITIVE LOGITS
     school
    0.18
    åŃ¦æł¡
    0.17
    åŃ¦æł¡çļĦ
    0.16
    school
    0.16
     schools
    0.15
    åľ¨åŃ¦æł¡
    0.14
     schooling
    0.14
    åŃ¸æł¡
    0.14
    ä¸ĬåѦ
    0.14
    schools
    0.13
    Activations Density 0.069%

    No Known Activations