© 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. 16745
    Prev
    Next
    INDEX
    Explanations

    the most

    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
    æŁIJç§į
    -0.11
    åIJĦç§į
    -0.11
    åĥı个
    -0.11
    缸åħ³æĶ¿çŃĸ
    -0.09
    缸åħ³äººåijĺ
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
     Various
    -0.09
    çļĦåIJĦç§į
    -0.09
    åIJĦ種
    -0.09
    åĪ°æĿ¥
    -0.09
    POSITIVE LOGITS
    å¾Ī好çļĦ
    0.11
    解èĦ±
    0.09
     Kardash
    0.08
    ä¸įéĶĻçļĦ
    0.08
    éĿŀ常好çļĦ
    0.08
    段
    0.08
     Kear
    0.08
    éĢı
    0.08
    شد
    0.08
    íħIJ
    0.08
    Activations Density 0.075%

    No Known Activations