© 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. 24283
    Prev
    Next
    INDEX
    Explanations

    firm offers services

    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
    该åİ¿
    -0.12
    ä»ĸçŁ¥éģĵ
    -0.10
    该éĻ¢
    -0.10
    çĿĢä»ĸ
    -0.09
    pek
    -0.09
    å½ĵä»ĸ
    -0.09
    ysz
    -0.09
    åijĬè¯ī她
    -0.08
    ä»ĸèĩªå·±
    -0.08
    æıIJåĪ°
    -0.08
    POSITIVE LOGITS
    æĪij们çļĦ
    0.27
    æĺ¯æĪij们
    0.26
    æĪij们
    0.24
    æĪij们å°Ĩ
    0.23
    æĪij们ä¼ļ
    0.23
     our
    0.22
    æĪijä»¬ä¹Ł
    0.22
    æĪijä»¬åľ¨
    0.22
    åĽłä¸ºæĪij们
    0.22
    æĪijåĢij
    0.21
    Activations Density 0.360%

    No Known Activations