© 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. 36638
    Prev
    Next
    INDEX
    Explanations

    product labeling for consumers

    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
    åıĮåIJij
    -0.09
    人çĶŁçļĦ
    -0.09
    æŀ¯
    -0.08
    åķ¼
    -0.08
    Chunks
    -0.08
    æĥħåķĨ
    -0.08
    èµĦæºIJæķ´åIJĪ
    -0.08
    è£ģåijĺ
    -0.07
    _bundle
    -0.07
    æł¼å°Ķ
    -0.07
    POSITIVE LOGITS
    让æ¶Īè´¹èĢħ
    0.16
    æ¶Īè´¹èĢħ
    0.15
    æ¶Īè´¹èĢħçļĦ
    0.12
    æ¶Īè²»èĢħ
    0.12
     consumers
    0.12
     Consumers
    0.11
    ä¹°åĪ°
    0.11
    è´Ńä¹°
    0.11
     consumer
    0.11
    .consumer
    0.11
    Activations Density 0.065%

    No Known Activations