© 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. 48826
    Prev
    Next
    INDEX
    Explanations

    diligent, meticulous, tedious, laborious, tireless

    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
    intage
    -0.11
    åIJĮç±»
    -0.09
    ynch
    -0.09
    åĩºå±Ģ
    -0.09
    çIJĨæĥ³ä¿¡å¿µ
    -0.08
    游æĪıä¸Ń
    -0.08
    ellan
    -0.08
    åľ¨çº¿åĴ¨è¯¢
    -0.08
    é£İäºij
    -0.08
    (TM
    -0.08
    POSITIVE LOGITS
    ç»Ĩèĩ´
    0.10
    翼
    0.10
    íŀĪ
    0.09
    éĴ»çłĶ
    0.09
    itude
    0.09
    æķ¬ä¸ļ
    0.09
    èļį
    0.09
     маÑģÑĤ
    0.08
    çĥ¦
    0.08
    ugged
    0.08
    Activations Density 0.018%

    No Known Activations