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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63454
    Prev
    Next
    INDEX
    Explanations

    sentence endings and conjunctions

    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
    ä½Ĩæĺ¯
    -0.17
     but
    -0.16
    ä½ĨçĶ±äºİ
    -0.16
    ä½Ĩä»ĸ
    -0.16
    ä½Ĩæĺ¯ä»ĸ
    -0.16
    ãģĦãģ¾ãģĻãģĮ
    -0.15
    ä½Ĩæĺ¯åľ¨
    -0.15
    ä½Ĩ
    -0.15
    ä½ĨæĪij们
    -0.15
    ä½Ĩ对äºİ
    -0.15
    POSITIVE LOGITS
     nonetheless
    0.19
    æ¯ķç«Ł
    0.17
    æ¯ķç«Łæĺ¯
    0.17
     nevertheless
    0.14
    ä»įæľī
    0.13
    çķ¢ç«Ł
    0.13
    åĨµä¸Ķ
    0.10
    åį´æĺ¯
    0.10
    以ä¸ĭæĺ¯
    0.10
    ä»įå°Ĩ
    0.10
    Activations Density 0.359%

    No Known Activations