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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20384
    Prev
    Next
    INDEX
    Explanations

    excitement and anticipation

    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
    èIJ½åĪ°
    -0.10
    éĢįéģ¥
    -0.09
    ä¸įåģľ
    -0.09
     Nass
    -0.09
    æĦıè¯ĨåĪ°
    -0.09
    éģĺ
    -0.09
    isser
    -0.09
    ä½İ头
    -0.09
    æ½
    -0.09
    ä¸įä¼ļæľī
    -0.09
    POSITIVE LOGITS
    æ¿ĢåĬ¨
    0.17
    åħ´å¥ĭ
    0.15
    -exc
    0.12
     excitement
    0.12
    æĮ¯å¥ĭ
    0.11
    人å¿ĥ
    0.11
     excited
    0.11
     Exc
    0.10
    _exc
    0.10
    æ¾İæ¹ĥ
    0.10
    Activations Density 0.033%

    No Known Activations