© 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. 40427
    Prev
    Next
    INDEX
    Explanations

    crystal, gem, ceramics

    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
    æ¯ı个人çļĦ
    -0.08
    jen
    -0.08
    vang
    -0.08
    coat
    -0.08
    çĽĶ
    -0.08
    乡éķĩ
    -0.08
    乡
    -0.08
     Apr
    -0.08
    乡æĿij
    -0.08
     Tin
    -0.08
    POSITIVE LOGITS
    æ°´æĻ¶
    0.11
    åĩ¿
    0.11
    æĻ¶
    0.11
    æĻ¶ä½ĵ
    0.11
    çIJ¢ç£¨
    0.11
    åŃĺè´§
    0.11
    åįıä¼ļä¼ļåijĺ
    0.10
    楸
    0.10
    èݹ
    0.10
    ç§ijåѦéĻ¢
    0.10
    Activations Density 0.109%

    No Known Activations