© 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. 51540
    Prev
    Next
    INDEX
    Explanations

    newly-appointed management and leadership titles

    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
    å¾Ĺèµ·
    -0.09
    窨
    -0.08
    ensex
    -0.08
    éĢ¸
    -0.08
    å°ĸ
    -0.08
    åłª
    -0.08
    ä¼¼çļĦ
    -0.08
    æİĴåIJį第
    -0.08
    iscrim
    -0.08
    çİĩåħĪ
    -0.08
    POSITIVE LOGITS
    æĽ¿æį¢
    0.11
    çļĦ带é¢Ĩ
    0.10
    åıĸ代
    0.10
     зло
    0.10
    贯彻
    0.09
    èī¯
    0.09
    é¢Ĩ导ä¸ĭ
    0.09
    çıŃåŃIJ
    0.09
    æį¢æĪIJ
    0.09
     replaced
    0.09
    Activations Density 0.081%

    No Known Activations