© 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. 26482
    Prev
    Next
    INDEX
    Explanations

    art and media forms

    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
    ä¸Ģä¼ļ
    -0.08
     QU
    -0.08
    ä¹Ŀ大
    -0.08
    æ¤Ĵ
    -0.08
    æĬ¥éģĵ称
    -0.08
    ounder
    -0.08
    atan
    -0.08
    ä¸įæĺ¯ä¸Ģ个
    -0.08
    é«ĺä»·
    -0.08
    æĬĬè¿Ļ个
    -0.08
    POSITIVE LOGITS
    åı£å¤´
    0.11
    ursions
    0.10
    伸æīĭ
    0.10
    еÑĩно
    0.10
    éĿ¢å¯¹éĿ¢
    0.09
    讲æķħäºĭ
    0.09
     immedi
    0.09
    éta
    0.09
    å£°éŁ³
    0.09
    å½¢å¼ı
    0.09
    Activations Density 0.155%

    No Known Activations