© 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. 29404
    Prev
    Next
    INDEX
    Explanations

    tired of

    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
    åIJIJ
    -0.10
    ives
    -0.09
    åĪ°ä½į
    -0.09
    ../../../
    -0.09
    arians
    -0.08
    æĸĻ
    -0.08
    ifi
    -0.08
    ever
    -0.08
    ennon
    -0.08
    ÙĬÙĨ
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.12
    è¿Ń
    0.09
    åĭĥåĭĥ
    0.09
    adic
    0.09
    åĤķ
    0.09
    è¤Ĵ
    0.09
    å»ĵ
    0.08
    ä¸¥æł¼æī§è¡Į
    0.08
    acist
    0.08
    éĺı
    0.08
    Activations Density 0.005%

    No Known Activations