© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12213
    Prev
    Next
    INDEX
    Explanations

    investing and selling

    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
    Negative Logits
    ç¥Ĺ
    -0.10
    jas
    -0.10
    æ±ĩ
    -0.09
    åĨ»
    -0.09
    ä¸ĸçķĮç»ıæµİ
    -0.09
    åºĦ严
    -0.09
    ä»İåݻ年
    -0.09
    æĪĸå¤ļæĪĸå°ij
    -0.09
    è¿ĪåIJij
    -0.09
    ä¼łæī¿
    -0.09
    POSITIVE LOGITS
    çīŁ
    0.12
    èİ·åĪ©
    0.11
    èµļ
    0.11
    æĬķæľº
    0.10
    å¥Ĺ
    0.10
    å¾Ĺ天
    0.09
    æĺ§
    0.09
    æĹ¶æľº
    0.09
     profit
    0.09
     PROF
    0.09
    Activations Density 0.086%

    No Known Activations