© 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. 11969
    Prev
    Next
    INDEX
    Explanations

    punctuations, clauses, and list connectors

    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»İ严
    -0.09
    è¸Ł
    -0.09
    æĬ¥åijĬ
    -0.08
    æľĢåıĹ欢è¿İ
    -0.08
    è¿Ħ
    -0.08
    å¯Ħæīĺ
    -0.08
    ç»ĵå±Ģ
    -0.08
    paring
    -0.08
    åīįçŀ»
    -0.08
    åĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    åıį驳
    0.14
    辩
    0.13
    驳
    0.12
     ìĺ¤íŀĪ볤
    0.12
    并ä¸įä¼ļ
    0.12
    ä¸įåŃĺåľ¨
    0.11
    æł¹æľ¬æ²¡æľī
    0.11
    ãģĿãĤĤãģĿãĤĤ
    0.11
     arguing
    0.11
    æł¹æľ¬ä¸į
    0.11
    Activations Density 0.091%

    No Known Activations