© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37083
    Prev
    Next
    INDEX
    Explanations

    more deaths

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĢåĪĩéĥ½
    -0.12
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.10
    ä¸ĢåĪĩ
    -0.10
    çĴŀ
    -0.10
    ä¸Ģä¸ĭåŃIJ
    -0.09
    é¦ĸæī¹
    -0.09
    ä¸Ģä¸ĭåŃIJå°±
    -0.09
    å¼ķ
    -0.09
    ä¸ĢæŶ
    -0.09
    å½ĺ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļæĪĸå°ij
    0.18
    ä¸įåIJĮç¨ĭ度
    0.15
    éĥ½æľī
    0.15
    è¦ģä¹Ī
    0.14
     either
    0.14
    éĥ½ä¼ļæľī
    0.13
    éĥ½æľīèĩªå·±
    0.12
    ë§Īëĭ¤
    0.12
    éĥ½ä¼ļ
    0.11
     ÙĪÙĥÙĦ
    0.11
    Activations Density 0.149%

    No Known Activations