© 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. 12374
    Prev
    Next
    INDEX
    Explanations

    license and copyright

    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
    éĴī
    -0.09
    боÑĢ
    -0.09
    íĮIJ
    -0.09
    è²Ĭ
    -0.08
    è¹Ī
    -0.08
    æľīèĩªå·±çļĦ
    -0.08
    åİĭ
    -0.08
    inese
    -0.08
    aleb
    -0.08
     zakÅĤad
    -0.08
    POSITIVE LOGITS
    æľīçĽĬ
    0.08
    æķ¦
    0.08
    çĿĽ
    0.08
    踵
    0.08
     intim
    0.08
    ä¸Ģè´¯
    0.07
    æĵħèĩª
    0.07
    åı¯ä¾Ľ
    0.07
    åħ¬ä¼Ĺ
    0.07
     cond
    0.07
    Activations Density 0.073%

    No Known Activations