© 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. 51866
    Prev
    Next
    INDEX
    Explanations

    aliens and space exploration

    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
    æ¯ıæľĪ
    -0.09
    èĢģåŃIJ
    -0.09
    èĩªåľ¨
    -0.09
    ä¸įæĸŃå®ĮåĸĦ
    -0.09
    -webpack
    -0.09
    å¨ħ
    -0.09
    ÐIJÐŀ
    -0.09
    é£İåIJ¹
    -0.09
    æ·ĭ
    -0.08
    å¿Į
    -0.08
    POSITIVE LOGITS
    åľ°çIJĥ
    0.11
    太空
    0.11
    ç§ijå¹»
    0.10
     завиÑģ
    0.10
     planet
    0.10
    é£ŀèĪ¹
    0.10
    æĺŁçIJĥ
    0.10
    ernaut
    0.09
    -earth
    0.09
     aliens
    0.09
    Activations Density 0.086%

    No Known Activations