© 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. 20418
    Prev
    Next
    INDEX
    Explanations

    reading fiction and non-fiction

    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
    å°ıåѦçĶŁ
    -0.14
    å°ıåѦ
    -0.13
    ä¸Ģ年级
    -0.12
    å°ıæľĭåıĭ
    -0.12
    ç«¥è£ħ
    -0.12
    åĦ¿ç«¥
    -0.11
    å¹¼åĦ¿
    -0.11
    ä¸Ńå°ıåѦçĶŁ
    -0.11
    ä¸Ńå°ıåѦ
    -0.11
    çİ©åħ·
    -0.10
    POSITIVE LOGITS
    ç»ħ
    0.10
    幺
    0.09
    峪
    0.09
    åĬłä»¥
    0.09
    ä¸ŃèĢĥ
    0.09
    éī´
    0.09
    é«ĺä¸ī
    0.08
    éĻIJå®ļ
    0.08
     Infer
    0.08
    æĴ·
    0.08
    Activations Density 0.070%

    No Known Activations