© 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. 17752
    Prev
    Next
    INDEX
    Explanations

    former followed by a title

    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
    çļĦ年轻人
    -0.10
    è¿Ļ群
    -0.10
    人群ä¸Ń
    -0.09
    ä¸Ģ群人
    -0.09
    æĸ°æ¨¡å¼ı
    -0.09
    ãĤ«ãĥķãĤ§
    -0.09
    太åIJİ
    -0.09
    ä¸Ģ群
    -0.09
    æĬĬæı¡
    -0.09
    åĪĨä¼ļ
    -0.09
    POSITIVE LOGITS
     former
    0.11
    Ñĥни
    0.10
    æĮļ
    0.09
     ÑįкÑģ
    0.09
    å°ĨåĨĽ
    0.09
    à¸Ĺหาร
    0.09
     drafts
    0.09
    è¿Ī
    0.09
    ä¿Ĭ
    0.09
     Linden
    0.08
    Activations Density 0.066%

    No Known Activations