© 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. 40230
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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
    年度
    -0.09
    å°ijä¸įäºĨ
    -0.09
    поÑĤ
    -0.08
    .Requires
    -0.08
     Signs
    -0.08
    âĺī
    -0.08
    èĤ¥
    -0.08
    crop
    -0.08
    驶
    -0.08
    æĴ®
    -0.08
    POSITIVE LOGITS
    次æķ°
    0.10
    æĪªèĩ³çĽ®åīį
    0.09
    èĥľ
    0.09
    è¿ĻçĤ¹
    0.09
    è¿ĩåī©
    0.08
    hammad
    0.08
    èĢģ人家
    0.08
    antes
    0.08
    &M
    0.08
    æĪĸå¤ļ
    0.08
    Activations Density 0.018%

    No Known Activations