© 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. 8687
    Prev
    Next
    INDEX
    Explanations

    business partnerships

    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
    å¯Ħ
    -0.09
    æļij
    -0.09
    archical
    -0.09
    nt
    -0.08
    ç»ĩ
    -0.08
    NT
    -0.08
    æ°ijæĦı
    -0.08
    .ACTION
    -0.08
    _fu
    -0.08
    olls
    -0.08
    POSITIVE LOGITS
    åIJĪä¼Ļ人
    0.16
    åIJĪä¼Ļ
    0.16
     partnership
    0.11
    åħ¼èģĮ
    0.10
    ä½ľåĿĬ
    0.10
    ç»ıèIJ¥æ¨¡å¼ı
    0.09
    æĬĬæīĭ
    0.09
    ç»ıèIJ¥
    0.09
    è´
    0.09
    æ¯ĶæĪij
    0.09
    Activations Density 0.033%

    No Known Activations