© 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. 7833
    Prev
    Next
    INDEX
    Explanations

    loan spell or loaned

    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
    åľŁè±ª
    -0.09
    å½Ŀ
    -0.09
    çļĦä¸ĢåĪĩ
    -0.09
    毳
    -0.09
    å¨ģ
    -0.09
    æĸĩåĮĸåĴĮ
    -0.09
    ä¾Ĺ
    -0.08
     known
    -0.08
    èĸ°
    -0.08
    åıĭè°Ĭ
    -0.08
    POSITIVE LOGITS
    触æij¸
    0.09
    åIJŀåĻ¬
    0.09
    çıŃ主任
    0.08
    纡
    0.08
    èĢIJ
    0.08
    ujet
    0.08
    åĩºåİ»
    0.08
    Affected
    0.08
    arda
    0.08
    åľ°å¸¦
    0.08
    Activations Density 0.007%

    No Known Activations