© 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. 6016
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence start

    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
    æīĢä»¥åľ¨
    -0.12
     therefore
    -0.10
    æīĢ以ä»ĸ
    -0.10
     поÑįÑĤомÑĥ
    -0.09
    åĽłæѤ
    -0.09
     ÐŁÐ¾ÑįÑĤомÑĥ
    -0.09
    åºĶ注æĦı
    -0.09
    æīĢ以
    -0.09
     nên
    -0.09
    es
    -0.08
    POSITIVE LOGITS
    以åħį
    0.12
    åIJ¦åĪĻ
    0.11
    以便
    0.11
    ä¸įçĦ¶
    0.11
     ê·¸ëŁ¬ë©´
    0.11
    箧
    0.10
    åIJ¦åīĩ
    0.10
    ä¹Łå¥½
    0.10
    好åIJĹ
    0.10
    ä¸įè¦ģ
    0.10
    Activations Density 0.061%

    No Known Activations