© 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. 24165
    Prev
    Next
    INDEX
    Explanations

    resources, sharing, stats, Arch, abstract

    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
     sunday
    -0.09
     subs
    -0.09
    æī§ä¸ļ
    -0.08
    æĬĦè¢Ń
    -0.08
    ä¸įçķĻ
    -0.08
    ç´łè´¨æķĻèĤ²
    -0.08
    ä¸Ģ对
    -0.08
    è¿ĿèĥĮ
    -0.08
    Reuse
    -0.08
    åįļè§Ī
    -0.08
    POSITIVE LOGITS
    oons
    0.11
    æ±Ŀ
    0.09
    _suffix
    0.09
    à¶Ń
    0.09
    fos
    0.09
    åħīçĶµ
    0.09
    åķIJ
    0.08
     Bethlehem
    0.08
    tti
    0.08
    å²±
    0.08
    Activations Density 0.040%

    No Known Activations