© 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. 52145
    Prev
    Next
    INDEX
    Explanations

    experience time pain success appearances

    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
    å¼Ģåı£
    -0.10
    ãģ¨ãģĦãģĨãģ®ãģĮ
    -0.09
    é»İæĺİ
    -0.09
    æ°ĹãģĮ
    -0.09
    Legacy
    -0.09
    anos
    -0.08
    âį
    -0.08
    å¹³å®ī
    -0.08
     Weg
    -0.08
    éģ¨
    -0.08
    POSITIVE LOGITS
    åij¼
    0.11
    åĨįå¤ļ
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    æĢª
    0.08
     wise
    0.08
    èĻ½
    0.08
    çĥĽ
    0.08
    enville
    0.08
     Barnett
    0.08
    æĺ¾å¾Ĺ
    0.08
    Activations Density 0.149%

    No Known Activations