© 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. 51992
    Prev
    Next
    INDEX
    Explanations

    tame, taming, untamed, domestication, sane

    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
    èĤĮ
    -0.10
    elles
    -0.10
    éħª
    -0.10
    累累
    -0.09
    ums
    -0.08
    اÙĩ
    -0.08
    樵
    -0.08
    TER
    -0.08
    icc
    -0.08
    带走
    -0.08
    POSITIVE LOGITS
    å¾Ĺä½ı
    0.10
    å·²ä¹ħçļĦ
    0.10
    åIJĪä½ľåħ±èµ¢
    0.10
    æ½ľ
    0.09
    éĶ¢
    0.09
    å±ĢéĿ¢
    0.09
    çĭ®åŃIJ
    0.09
    èĽ®
    0.09
    æ»ļåĬ¨
    0.09
    æķ´é¡¿
    0.09
    Activations Density 0.008%

    No Known Activations