© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26748
    Prev
    Next
    INDEX
    Explanations

    opening and closing of establishments

    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
    è§īæĤŁ
    -0.10
    æĿ¥èĩªäºİ
    -0.09
    áb
    -0.09
     Pharmaceuticals
    -0.09
    个交æĺĵ
    -0.09
    ะ
    -0.08
    èĥ¸éĥ¨
    -0.08
    IDD
    -0.08
    bourg
    -0.08
    ç®ĢåİĨ
    -0.08
    POSITIVE LOGITS
    å¼Ģä¸ļ
    0.18
    èIJ¥ä¸ļ
    0.18
    ç»ıèIJ¥èĢħ
    0.13
    åĢĴéĹŃ
    0.13
    ç»ıèIJ¥
    0.13
    åģ¥èº«æĪ¿
    0.12
    å¼ĢåĬŀ
    0.12
    è¯ķè¡Į
    0.12
    ç»ıèIJ¥æ¨¡å¼ı
    0.12
    åĬŀåѦ
    0.12
    Activations Density 0.366%

    No Known Activations