© 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. 52236
    Prev
    Next
    INDEX
    Explanations

    repetition of again

    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
    ä¸ĢåIJij
    -0.12
    ä¸Ģ缴
    -0.10
     mpl
    -0.10
    tam
    -0.08
    带走
    -0.08
    ãģĦãģĨ
    -0.07
    ä¸ĢçĽ´ä»¥æĿ¥
    -0.07
    ze
    -0.07
    added
    -0.07
     conquered
    -0.07
    POSITIVE LOGITS
    éĨĩ
    0.10
    éĩįä»»
    0.10
    æIJħ
    0.10
    åıijæĮ¥
    0.10
    ë¡ľìĦľ
    0.09
    èķĪ
    0.09
    é«ĺ涨
    0.09
    强çĥĪ
    0.09
    æ¯Ķä¸Ĭå¹´
    0.09
    ä¸Ĭè°ĥ
    0.09
    Activations Density 0.025%

    No Known Activations