© 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. 20602
    Prev
    Next
    INDEX
    Explanations

    cheese factories

    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
    迤
    -0.12
    éĻª
    -0.10
    çħ²
    -0.10
    æĺ¥è¿IJ
    -0.09
    azon
    -0.09
    èĵ¼
    -0.08
    è¾ĩ
    -0.08
    ÇĴ
    -0.08
    çħ¨
    -0.08
    å·´å·´
    -0.08
    POSITIVE LOGITS
    ä¹³ä¸ļ
    0.12
    奶
    0.12
    èĪŁå±±
    0.10
    TintColor
    0.10
    ÙĪبر
    0.10
     sữa
    0.10
    éħª
    0.09
    åĪ¶åĵģ
    0.09
     dairy
    0.09
    æ¾Ħ
    0.09
    Activations Density 0.083%

    No Known Activations