© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    payment and financial obligations

    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
    èĩªåѦ
    -0.09
    å¥ł
    -0.09
    è¦ģåİ»
    -0.09
    驾车
    -0.09
    weg
    -0.08
    èĦ±é¢ĸèĢĮåĩº
    -0.08
    æĬ¬èµ·å¤´
    -0.08
    {{{
    -0.08
    ä¸Ģ人
    -0.08
    facet
    -0.08
    POSITIVE LOGITS
    æĭĸæ¬ł
    0.15
    æ»ŀ
    0.15
    è¿Ł
    0.14
    èµĬ
    0.12
    æ±ĩ
    0.10
    ç»ĵç®Ĺ
    0.10
     Holidays
    0.10
    éģ²
    0.10
    款
    0.09
    åĮ¯
    0.09
    Activations Density 0.059%

    No Known Activations