© 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. 55718
    Prev
    Next
    INDEX
    Explanations

    often makes something

    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
    究竣æĺ¯
    -0.11
    æĺ¾çĦ¶
    -0.10
    å½ĵçĦ¶
    -0.10
    ä¼¼ä¹İ
    -0.10
     apparently
    -0.09
    éĻĮ
    -0.09
    æį®è¯´
    -0.09
     presumably
    -0.09
    çľĭæĿ¥
    -0.09
    éĻĮçĶŁäºº
    -0.09
    POSITIVE LOGITS
    æľīå¿ħè¦ģ
    0.11
    uten
    0.11
    åıĹçĽĬ
    0.09
    è¿Ļ对
    0.09
     займ
    0.09
    æĽ´éĢĤåIJĪ
    0.09
    åĬ¨èį¡
    0.09
     ÙĪØ£ÙĨ
    0.09
    è¿Ļ对äºİ
    0.08
    æ¯ĶæĪij
    0.08
    Activations Density 0.130%

    No Known Activations