© 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. 32402
    Prev
    Next
    INDEX
    Explanations

    specific dates and financial levels

    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
    mare
    -0.10
    计éĩı
    -0.09
     baÅŁÄ±na
    -0.09
    metro
    -0.09
    æķ´ä¸ªäºº
    -0.09
    ä¸¤å¼ł
    -0.09
    讨
    -0.09
    дж
    -0.09
    æĸĩåĪĽ
    -0.08
     Lindsey
    -0.08
    POSITIVE LOGITS
    触åıĬ
    0.09
    大äºĭ
    0.09
    æĮĤ
    0.09
    è´§æºIJ
    0.08
    å¤ļæĸ¹
    0.08
    ündig
    0.08
    åĪļ
    0.08
    åĢ¼çıŃ
    0.08
    ç©´
    0.08
    iosa
    0.08
    Activations Density 0.039%

    No Known Activations