© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47758
    Prev
    Next
    INDEX
    Explanations

    that year/day/evening

    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
    ä¸įåĬ¨
    -0.10
    ellen
    -0.09
     Permanent
    -0.09
    度è¿ĩ
    -0.08
    褥
    -0.08
    é¾Ł
    -0.08
     поÑģÑĤоÑıн
    -0.08
    åĽ¢
    -0.08
    çģ¯
    -0.08
    å©Ĩ
    -0.08
    POSITIVE LOGITS
    æĻĤåĢĻ
    0.15
    æĹ©ä¸Ĭ
    0.14
    æŶåĢĻ
    0.12
    æĻļä¸Ĭ
    0.12
    æĹ¥åľ¨
    0.12
    è¿Ļä¸Ģå¹´
    0.12
    å½ĵæĻļ
    0.12
    ä¸įä¹ħ
    0.11
     day
    0.11
    éĤ£ä¸Ģ天
    0.10
    Activations Density 0.185%

    No Known Activations