© 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. 21181
    Prev
    Next
    INDEX
    Explanations

    holiday expressions

    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
    å¾ĪæŃ£å¸¸
    -0.09
    éĤ£ä½į
    -0.09
    äºĭåĦ¿
    -0.08
    æѤäºĭ
    -0.08
    好çľĭ
    -0.08
    é»ĺ
    -0.08
    åĽ¿
    -0.08
     credit
    -0.08
    æŃ¤äºº
    -0.08
    åľ¨è¿ĩ渡
    -0.08
    POSITIVE LOGITS
    åĮħåIJ«äºĨ
    0.10
    èªĵ
    0.10
    ç»ıèIJ¥çIJĨ念
    0.09
    éĢļä¿Ĺ
    0.09
    à¹ģห
    0.09
    ç®Ģ称
    0.09
    æģŃ
    0.09
    ç«ĭ足
    0.08
    å®ĹæŨ
    0.08
    æīĢ以æĪij们
    0.08
    Activations Density 0.126%

    No Known Activations