© 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. 8695
    Prev
    Next
    INDEX
    Explanations

    USC, California, CA abbreviations

    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
    ä¸Ńç§ij
    -0.11
    zelf
    -0.10
    fans
    -0.09
    UGE
    -0.08
    åĩºè·¯
    -0.08
     bè
    -0.08
    cookies
    -0.08
    uns
    -0.08
     PSU
    -0.08
    å©Ĩ
    -0.08
    POSITIVE LOGITS
    纶
    0.10
    çĦ¶æĺ¯
    0.09
     wewnÄĻtrzn
    0.09
    è¶Ĭæĺ¯
    0.09
    /type
    0.08
    aid
    0.08
    mai
    0.08
    ÙĬÙĨا
    0.08
     تÙĤدÙĬ
    0.08
    ä¹IJæĦı
    0.08
    Activations Density 0.008%

    No Known Activations