© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9074
    Prev
    Next
    INDEX
    Explanations

    pursue positive goals and life

    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
    æĺİçĻ½
    -0.09
    æ»ŀåIJİ
    -0.09
    æİĪ
    -0.08
    羸
    -0.08
    åĬ¿
    -0.08
    ä¸Ģä½ĵåĮĸ
    -0.08
    _PAGES
    -0.08
    åı¯æĢľ
    -0.08
    为æ°ij
    -0.08
    æ¼Ķ
    -0.08
    POSITIVE LOGITS
    çļĦ人çĶŁ
    0.14
    çĶŁæ´»çļĦ
    0.12
    人çĶŁ
    0.12
    人çĶŁçļĦ
    0.11
    çIJIJ
    0.11
     life
    0.11
    æľīæĦıä¹ī
    0.11
     Life
    0.11
    Life
    0.11
    ç¾İ好
    0.11
    Activations Density 0.210%

    No Known Activations