© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 615
    Prev
    Next
    INDEX
    Explanations

    both us our mutual agreement

    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
    é¢ĺ主
    -0.10
    人为
    -0.09
    ä¸ŃåĽ½ä¼ģä¸ļ
    -0.09
    åĽ¢åľĨ
    -0.09
    欺
    -0.09
    åķ¼
    -0.09
    å®ŀç͍æĢ§
    -0.09
    åįĸ
    -0.08
    holm
    -0.08
    urette
    -0.08
    POSITIVE LOGITS
    åIJĦèĩª
    0.12
    åIJĦèĩªçļĦ
    0.11
    纵
    0.10
    åħ±åIJĮ
    0.10
    ãģĬäºĴãģĦ
    0.09
    dü
    0.09
    æīĢå±ŀ
    0.09
     mutually
    0.09
    è§ĦèĮĥ
    0.09
     respective
    0.08
    Activations Density 0.059%

    No Known Activations