© 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. 21017
    Prev
    Next
    INDEX
    Explanations

    refreshing page

    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
     Claus
    -0.09
    ä¾Ŀ
    -0.08
    ç¹ģå¿Ļ
    -0.08
    çİ°éĺ¶æ®µ
    -0.08
    æĽĽ
    -0.08
    busy
    -0.08
     Hale
    -0.08
     Aç
    -0.08
    æĶ¶ç¼©
    -0.08
    ä¸Ģå¹´ä¸Ģ度
    -0.08
    POSITIVE LOGITS
    ç»ĩ
    0.10
    åѬ
    0.09
    å¼ĵ
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    ahu
    0.09
    itch
    0.09
    åħ¨åªĴä½ĵ
    0.08
    åıĪèĥ½
    0.08
    lat
    0.08
    èªĵè¨Ģ
    0.08
    Activations Density 0.005%

    No Known Activations