© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54735
    Prev
    Next
    INDEX
    Explanations

    education, school, labor

    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
    æľĢåIJİä¸Ģ次
    -0.10
    åĩ¡äºĭ
    -0.10
    亢
    -0.09
     ÑĩÑĥÑĤÑĮ
    -0.08
    åĬ©
    -0.08
    åĵģä½į
    -0.08
    å¤ĸåĮħ
    -0.08
    utura
    -0.08
    åѤç«ĭ
    -0.08
    uer
    -0.08
    POSITIVE LOGITS
    ä¸ĬåѦ
    0.13
    è¾į
    0.12
    ä¹īåĬ¡æķĻèĤ²
    0.11
    塾
    0.10
    樵
    0.10
    åºĶåıĬæŶ
    0.09
     schooling
    0.09
    çļĦåŃ©åŃIJ
    0.09
    æĤ¨çļĦåŃ©åŃIJ
    0.09
    à¹Ĥรà¸ĩ
    0.09
    Activations Density 0.031%

    No Known Activations