© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51637
    Prev
    Next
    INDEX
    Explanations

    's contraction

    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
    æĪĸ许æĺ¯
    -0.13
    åĪ°åºķæĺ¯
    -0.11
    ä¹Łè®¸æĺ¯
    -0.10
    æıŃå¼Ģ
    -0.09
    æľĢç¾İçļĦ
    -0.09
    éķ³
    -0.09
    è®®ä¼ļ
    -0.09
    åŀ«
    -0.09
    åį´åıijçİ°
    -0.09
    èĩ³åħ³
    -0.09
    POSITIVE LOGITS
    çĪ±ç¾İ
    0.10
    æľīå¾Īå¤ļ
    0.09
    æľīä¸ĢäºĽ
    0.09
    èµ·æĿ¥äºĨ
    0.09
    atts
    0.08
    åįĥæĸ¹
    0.08
    ÐŁÐ¾Ð´ÑĢобнее
    0.08
    ë§ŀ
    0.08
    à¸Īำà¸ģ
    0.08
    -thumbnails
    0.08
    Activations Density 0.049%

    No Known Activations