© 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. 16556
    Prev
    Next
    INDEX
    Explanations

    growth and size changes

    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
    çģ¶
    -0.11
    ru
    -0.09
    ple
    -0.08
    odem
    -0.08
     fmt
    -0.08
    åİĭåĬĽ
    -0.08
    é«ĺä½İ
    -0.08
    çĨ¨
    -0.08
    å¥ij
    -0.08
     kém
    -0.08
    POSITIVE LOGITS
    éķ¿å¤§
    0.21
    æĪIJéķ·
    0.19
    æĪIJéķ¿
    0.19
    æĪIJéķ¿ä¸º
    0.18
    åģ¥åº·æĪIJéķ¿
    0.18
    éķ¿å¤§äºĨ
    0.17
    æĪIJ人
    0.16
    çļĦæĪIJéķ¿
    0.15
    Growing
    0.14
    çĶŁéķ¿
    0.13
    Activations Density 0.071%

    No Known Activations