© 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. 59350
    Prev
    Next
    INDEX
    Explanations

    being fooled or prey

    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
     Slice
    -0.10
    人åĬĽ
    -0.09
     Vie
    -0.09
    äºī夺
    -0.08
    èĪį
    -0.08
    oli
    -0.08
     slice
    -0.08
    åĮ¿
    -0.08
     Category
    -0.08
    æ´Ĵ
    -0.08
    POSITIVE LOGITS
    被éªĹ
    0.17
    åĤ»
    0.14
    å¹¼ç¨ļ
    0.14
     naive
    0.13
     naï
    0.12
    å¤©çľŁ
    0.12
    æĹłçŁ¥
    0.12
    åĨ²åĬ¨
    0.11
     sucker
    0.11
    æĦļ
    0.11
    Activations Density 0.087%

    No Known Activations