© 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. 19276
    Prev
    Next
    INDEX
    Explanations

    teacher and school concepts

    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
    åħ¥åѦ
    -0.09
    æĢ»è£ģ
    -0.09
    éĢł
    -0.09
    pekt
    -0.09
    åľ¨äº¬
    -0.09
    èĩªåĬ©
    -0.09
    åķĨæĬ¥
    -0.08
    åĽ´ç»ķ
    -0.08
    utra
    -0.08
    çļĦåŃ¦ä¹ł
    -0.08
    POSITIVE LOGITS
    æī§æķĻ
    0.20
    æķĻå¸Ī
    0.19
     teaching
    0.18
    æķĻ師
    0.17
    æķĻèĤ²æķĻåѦ
    0.17
    æķĻåѦ
    0.17
    ä»»æķĻ
    0.16
    诲
    0.16
    课åłĤæķĻåѦ
    0.16
    æİĪ课
    0.16
    Activations Density 0.112%

    No Known Activations