© 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. 59369
    Prev
    Next
    INDEX
    Explanations

    as well

    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
    è³ĵ
    -0.10
    ASA
    -0.10
    å¥ij
    -0.09
     Natal
    -0.09
    بÙĪر
    -0.09
    atal
    -0.08
    аÑĩ
    -0.08
    ix
    -0.08
    ä¸¥æł¼æĮīçħ§
    -0.08
    宾
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.13
    ä¹Łæĺ¯å¦ĤæѤ
    0.12
    çľ¼éĥ¨
    0.11
     ÑĤоже
    0.11
    çŁ£
    0.11
    导读
    0.10
     alike
    0.10
    è¹ij
    0.09
    ìĶ©
    0.09
    ä¹Łæľīä¸ĢäºĽ
    0.09
    Activations Density 0.042%

    No Known Activations