© 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. 59249
    Prev
    Next
    INDEX
    Explanations

    licensed under

    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
    æķĽ
    -0.09
    ãģıãĤĮ
    -0.09
    LLL
    -0.08
     Panic
    -0.08
     Kra
    -0.08
    ç±į
    -0.08
    esco
    -0.08
    赢家
    -0.08
    Explore
    -0.07
    é³
    -0.07
    POSITIVE LOGITS
    åijķ
    0.09
    åĬŀåѦ
    0.09
    解çŃĶ
    0.09
    еÑĢа
    0.09
    ç§ģç«ĭ
    0.09
    .priv
    0.09
    veau
    0.09
    าะ
    0.08
    åĩºçĤī
    0.08
    太éĺ³åŁİ
    0.08
    Activations Density 0.004%

    No Known Activations