© 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. 40281
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
    ä¸įåĨįæĺ¯
    -0.12
    ä¸įçĪ±
    -0.11
    ä¸įåĨį
    -0.10
    ä¸į说
    -0.10
    пÑĢавлен
    -0.10
    åį´æ²¡æľī
    -0.10
    åį´ä¸į
    -0.09
    ä¸įæĪIJ
    -0.09
     неÑĤ
    -0.09
    ä¸įåİ»
    -0.09
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.16
    çħ§æł·
    0.10
     sondern
    0.09
     nor
    0.09
     Bridges
    0.08
    ç«ŀ
    0.08
    çŁ¥åIJįåĵģçīĮ
    0.08
    äºĮæīĭ
    0.08
    å·§å¦Ļ
    0.08
    èĻİ
    0.08
    Activations Density 0.055%

    No Known Activations