© 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. 20444
    Prev
    Next
    INDEX
    Explanations

    human existence and condition

    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
    çļĦèģĮä¸ļ
    -0.09
    æ°´åŁŁ
    -0.09
    çIJĨæĥ³çļĦ
    -0.08
    çļĦåľ°
    -0.08
    è¾ĩ
    -0.08
    çľ¼ä¸Ń
    -0.08
    导åIJij
    -0.08
    REV
    -0.08
    åŁ¹åħ»åѦçĶŁ
    -0.08
    çľ¼éĩĮ
    -0.08
    POSITIVE LOGITS
     human
    0.22
    人æĢ§
    0.21
    人类
    0.21
     Ñĩелов
    0.20
    human
    0.17
    -human
    0.17
    人é¡ŀ
    0.16
    _human
    0.15
     humans
    0.15
    人å¿ĥ
    0.14
    Activations Density 0.088%

    No Known Activations