© 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. 8011
    Prev
    Next
    INDEX
    Explanations

    imprint, print, printing

    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
    为ä¹ĭ
    -0.09
    enerate
    -0.09
     اÙĦÙħÙĨا
    -0.09
    æĬ±
    -0.09
    ä¹İ
    -0.08
    è´Łè´£ä»»
    -0.08
    çĺ¦èº«
    -0.08
    cmc
    -0.08
    è¯ŀ
    -0.08
    rou
    -0.08
    POSITIVE LOGITS
    umba
    0.10
    累累
    0.10
    INGS
    0.10
    ç¨İåĬ¡æĢ»å±Ģ
    0.09
    åѤåįķ
    0.09
    ecd
    0.09
    好æĦŁ
    0.09
    峦
    0.09
    edly
    0.09
    ponder
    0.08
    Activations Density 0.007%

    No Known Activations