© 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. 24180
    Prev
    Next
    INDEX
    Explanations

    activities and events

    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
    addin
    -0.10
    åºĬä¸Ĭ
    -0.09
    æĢ»ä»·
    -0.09
    ä¸Ģ家
    -0.08
    alone
    -0.08
     Ritual
    -0.08
    ฤ
    -0.08
    奢
    -0.08
    ukes
    -0.08
    esktop
    -0.08
    POSITIVE LOGITS
    çŃ¾åIJį
    0.09
    æľº
    0.09
    Zen
    0.09
    æ¯Ľ
    0.08
    ival
    0.08
    设ç«ĭ
    0.08
    iec
    0.08
    æĬ½å¥ĸ
    0.08
    dash
    0.08
    leck
    0.08
    Activations Density 0.082%

    No Known Activations