© 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. 31687
    Prev
    Next
    INDEX
    Explanations

    highlights and notable things

    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
    çķĮçļĦ
    -0.09
    å¾ĢåIJİ
    -0.09
    GED
    -0.09
    æĽĮ
    -0.08
    æĹºçĽĽ
    -0.08
    æł¹æľ¬æ²¡æľī
    -0.08
    çķĮéĻIJ
    -0.08
    ä¸įå¼Ģ
    -0.08
    åįŀ
    -0.08
    å·´
    -0.08
    POSITIVE LOGITS
    亮çĤ¹
    0.20
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.13
    èİ«è¿ĩäºİ
    0.13
     standout
    0.13
    精彩
    0.11
    åĢ¼å¾Ĺ注æĦı
    0.11
    ä¸Ģå¹ķ
    0.11
    åį°è±¡æ·±åĪ»
    0.11
     notable
    0.10
    çľĭçĤ¹
    0.10
    Activations Density 0.052%

    No Known Activations