© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8989
    Prev
    Next
    INDEX
    Explanations

    low-fat, healthy eating

    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
    ä½ĵä¼ļ
    -0.09
    纽
    -0.08
     strat
    -0.08
    饱满
    -0.08
    ç»ıéªĮ丰å¯Į
    -0.08
    è¡¥é½IJ
    -0.08
    rome
    -0.08
    5
    -0.08
    Pipe
    -0.08
    ä¸įæŃ»
    -0.08
    POSITIVE LOGITS
    æĽ¿ä»£
    0.12
    绿èī²çݯä¿Ŀ
    0.12
     Altern
    0.11
     alternatives
    0.11
    èĬĤèĥ½çݯä¿Ŀ
    0.11
    Altern
    0.11
    ä½İ碳
    0.10
    磫
    0.10
    绿èī²
    0.10
    æĽ¿æį¢
    0.10
    Activations Density 0.091%

    No Known Activations