© 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. 23946
    Prev
    Next
    INDEX
    Explanations

    times and time zones

    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
     roma
    -0.10
    .bpm
    -0.10
    æĪij们ä¸Ģèµ·
    -0.10
    ru
    -0.09
    訾
    -0.09
    é¾Ħ
    -0.08
    è¡Ķ
    -0.08
    åľ¨ä¹İ
    -0.08
    isode
    -0.08
    æľīä»·åĢ¼çļĦ
    -0.08
    POSITIVE LOGITS
    讫
    0.08
    ennes
    0.08
    áĢĺ
    0.08
    Leaks
    0.08
     Tight
    0.08
    æĥķ
    0.08
    åħļé£İ
    0.08
    inka
    0.08
    arya
    0.08
    éľİ
    0.08
    Activations Density 0.020%

    No Known Activations