© 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. 37467
    Prev
    Next
    INDEX
    Explanations

    manufacturing and company founding

    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
    اÙĩر
    -0.10
    anga
    -0.09
    è¢Ĵ
    -0.09
    äºĮæīĭæĪ¿
    -0.08
    ä¸ĩè¾¾
    -0.08
    abus
    -0.08
    èµĦ管
    -0.08
    å¢ŀæ·»äºĨ
    -0.08
    åĬŀ好
    -0.08
    TemplateName
    -0.08
    POSITIVE LOGITS
    åĪ¶éĢł
    0.16
    ç»ıéĶĢ
    0.14
     product
    0.14
    åĪ¶éĢłåķĨ
    0.14
     manufacturing
    0.14
    éĶĢåĶ®
    0.14
    çłĶåıij
    0.14
     Manufacturing
    0.14
     ìłľíĴĪ
    0.13
     manufacturer
    0.13
    Activations Density 0.163%

    No Known Activations