© 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. 48179
    Prev
    Next
    INDEX
    Explanations

    real estate and urban development

    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
    ä½İ温
    -0.09
    abinet
    -0.09
    unal
    -0.09
    abble
    -0.09
    åĬ£åĬ¿
    -0.09
     Gross
    -0.09
    èĮ´
    -0.08
    rench
    -0.08
    agement
    -0.08
     wiÄĻ
    -0.08
    POSITIVE LOGITS
    å¼Ģåıij
    0.14
    å¼Ģåıij建设
    0.12
    éĸĭçĻ¼
    0.10
    ç«ĸ
    0.10
    åķĨä¸ļ
    0.10
    建éĢł
    0.10
     golf
    0.10
    å¼ĢåıijèĢħ
    0.10
    é¥ŃåºĹ
    0.09
    åŁİå¸Ĥ建设
    0.09
    Activations Density 0.093%

    No Known Activations