© 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. 47518
    Prev
    Next
    INDEX
    Explanations

    discover, know, see, say, announce, think

    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
    oka
    -0.10
     Countdown
    -0.08
    ä½ıæĪ¿
    -0.08
    åijĬ
    -0.08
     Grinder
    -0.08
    .same
    -0.08
    æĪĹ
    -0.08
     Toolbar
    -0.08
    SN
    -0.08
     Karn
    -0.08
    POSITIVE LOGITS
    íģ¼
    0.09
    æľīå¤ļä¹Ī
    0.08
    æľīå¤ļ
    0.08
    overall
    0.08
    ç»ıéªĮåĴĮ
    0.08
    à¹īม
    0.08
    å±ħçĦ¶
    0.08
    ÑĤика
    0.08
    两个人
    0.08
    人身
    0.08
    Activations Density 0.021%

    No Known Activations