© 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. 60844
    Prev
    Next
    INDEX
    Explanations

    went on to take action

    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
    iese
    -0.09
    们éĥ½
    -0.09
    æ¯Ĵç´ł
    -0.09
    isto
    -0.09
    åħ¶ä¸Ńæľī
    -0.09
    çĶļèĩ³è¿ŀ
    -0.09
    ÑĥлÑĮ
    -0.09
    对ä¸įèµ·
    -0.08
    FLT
    -0.08
    é©Ń
    -0.08
    POSITIVE LOGITS
    为客æĪ·
    0.09
    第ä¸Ģä½į
    0.08
    /down
    0.08
    游æĪıå½ĵä¸Ń
    0.08
     success
    0.08
    anje
    0.07
    第
    0.07
    ced
    0.07
    æĪIJ为ä¸Ģ个
    0.07
    åįģå¤ļ
    0.07
    Activations Density 0.007%

    No Known Activations