© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62389
    Prev
    Next
    INDEX
    Explanations

    Asian countries

    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
    éķ¿éķ¿
    -0.10
    è½®åĽŀ
    -0.09
    oux
    -0.09
    æĦı大
    -0.09
    avit
    -0.09
    spir
    -0.09
    两ä¸ī
    -0.09
    ä¸ĭ次
    -0.09
    å®ŀåľ¨å¤ª
    -0.08
    ç¼Ł
    -0.08
    POSITIVE LOGITS
    å²ļ
    0.10
    åįĥæĸ¹çĻ¾è®¡
    0.07
    åħ¶ä¸ŃåĮħæĭ¬
    0.07
    à¸Ĥà¸Ļ
    0.07
    åľī
    0.07
    åĪĨä¼ļ
    0.07
    åĶĽ
    0.07
    æ¯ĶåĪ©
    0.07
    ystem
    0.07
    ren
    0.07
    Activations Density 0.215%

    No Known Activations