© 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. 21299
    Prev
    Next
    INDEX
    Explanations

    deal, cooperation, ordered, Africa, bloc, countries, Chinese

    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
    ÑĥлÑĮ
    -0.09
    åĿIJ
    -0.08
    èĬĿ
    -0.08
    Parm
    -0.08
    iate
    -0.08
    请åģĩ
    -0.08
     wre
    -0.07
    éļ¶å±ŀäºİ
    -0.07
    æľĿ
    -0.07
    REEN
    -0.07
    POSITIVE LOGITS
    æı´åĬ©
    0.13
    å¤ĸæı´
    0.12
    æĹłåģ¿
    0.11
    顾éĹ®
    0.11
    è´Ńä¹°
    0.11
    ä¾Ľè´§
    0.10
     viá»ĩn
    0.10
     lắp
    0.10
    ä¸Ńæĸ¹
    0.10
     equipment
    0.10
    Activations Density 0.250%

    No Known Activations