© 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. 40416
    Prev
    Next
    INDEX
    Explanations

    comprehensive coverage, review, analysis, comparison

    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
    éĩįè¦ģä½ľçĶ¨
    -0.10
    ç¥ŀä»Ļ
    -0.09
    éĵ®
    -0.09
    å³¥
    -0.09
    zed
    -0.08
    ä¼łçľŁ
    -0.08
    ç¾İ好çĶŁæ´»
    -0.08
    çĹ´
    -0.08
     intim
    -0.08
    çĸijéĹ®
    -0.08
    POSITIVE LOGITS
     coverage
    0.11
    è¦ĨçĽĸ
    0.11
    holm
    0.10
     Coverage
    0.10
     thoroughly
    0.10
    纵
    0.10
    åħ¨éĿ¢
    0.10
     lan
    0.09
    ummer
    0.09
    Coverage
    0.09
    Activations Density 0.064%

    No Known Activations