© 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. 40296
    Prev
    Next
    INDEX
    Explanations

    time for or time to

    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
    Negative Logits
    rys
    -0.10
    广éĺĶ
    -0.09
    udson
    -0.09
    æī©
    -0.09
    çĽĬ
    -0.09
    ä¸ľäº¬
    -0.09
    ç«Ļ
    -0.09
    å°±è·Ł
    -0.09
    minster
    -0.09
    roach
    -0.09
    POSITIVE LOGITS
     time
    0.11
    æĹ¶æľº
    0.11
    æŶåĢĻ
    0.11
    æŶéĹ´
    0.10
     اÙĦÙĪÙĤت
    0.09
    time
    0.09
    æĻĤéĸĵ
    0.09
    åĪ°äºĨ
    0.09
    èĢģæŧ
    0.09
    æĮ½
    0.08
    Activations Density 0.061%

    No Known Activations