© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    children and preschool 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
    对åѦçĶŁ
    -0.11
    ervo
    -0.10
    çĶ·çĶŁ
    -0.10
    æ¸Ĭ
    -0.09
    飧
    -0.09
    ä¾ł
    -0.09
    åѦçĶŁ
    -0.09
    æĸĭ
    -0.09
    zier
    -0.09
    åįĥç±³
    -0.09
    POSITIVE LOGITS
    ç«ĭä½ĵ
    0.11
    å¹¼åĦ¿åĽŃ
    0.11
    çİ©åħ·
    0.11
    å¹¼åĦ¿
    0.11
    å©´åĦ¿
    0.10
    åѦåīįæķĻèĤ²
    0.10
     toys
    0.10
    åѦåīį
    0.10
    å¹¼ç¨ļ
    0.10
    çļĦ第ä¸Ģ个
    0.10
    Activations Density 0.129%

    No Known Activations