© 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. 20814
    Prev
    Next
    INDEX
    Explanations

    IEEE 802.11 standard

    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
    _OW
    -0.10
    é£Ĵ
    -0.10
    人æŃ»äº¡
    -0.09
    èģ·
    -0.09
     полÑĥÑĩен
    -0.08
    建ç«ĭäºĨ
    -0.08
    çĭ¬ä¸Ģ
    -0.08
    æѦèѦ
    -0.08
    éĥ¨ä»½
    -0.08
    eted
    -0.08
    POSITIVE LOGITS
     standards
    0.11
    è¶ĭ
    0.10
    æłĩåĩĨ
    0.09
    æ¡Ĩæŀ¶åįıè®®
    0.08
    åħħ
    0.08
    åĪ¶è£ģ
    0.08
    ä¼łå¯¼
    0.08
    iram
    0.08
    é«ĺæłĩåĩĨ
    0.08
     standard
    0.08
    Activations Density 0.141%

    No Known Activations