© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59335
    Prev
    Next
    INDEX
    Explanations

    developing 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
    Negative Logits
    urm
    -0.09
    ег
    -0.09
     Hil
    -0.09
    plen
    -0.08
    é«ĺæłĩåĩĨ
    -0.08
     Hillary
    -0.08
    ä¸įåĪ°
    -0.08
    di
    -0.08
    _DIAG
    -0.08
    arsed
    -0.08
    POSITIVE LOGITS
    ä¿ĿçķĻ
    0.10
    åľ°åĮºçļĦ
    0.10
    éĺµèIJ¥
    0.09
    æľīåĪ©
    0.08
    æľĭåıĭ们
    0.08
    åĨľä¸ļ大åѦ
    0.08
     forg
    0.08
    æģ¶æĢ§
    0.08
    /Search
    0.08
    尤为
    0.08
    Activations Density 0.172%

    No Known Activations