© 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. 24178
    Prev
    Next
    INDEX
    Explanations

    stories and myths

    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
    çļĦèģĮä¸ļ
    -0.10
    è¶Ł
    -0.09
    åķ¡
    -0.09
    ç¬ijèĦ¸
    -0.09
    çļĦ认åı¯
    -0.08
    è¡®
    -0.08
    å¾½
    -0.08
    æ¦ķ
    -0.08
    rophy
    -0.08
    gate
    -0.08
    POSITIVE LOGITS
    ä¼łè¯´
    0.22
    ä¼łéĹ»
    0.18
     legends
    0.16
     rumors
    0.16
     legend
    0.15
    æķħäºĭ
    0.14
     rumor
    0.14
     rumours
    0.14
    ä¼łè¨Ģ
    0.14
    Legend
    0.13
    Activations Density 0.057%

    No Known Activations