© 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. 36873
    Prev
    Next
    INDEX
    Explanations

    eliminate or away

    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
    æİİ
    -0.10
    ологии
    -0.09
    æľ¬è´¨ä¸Ĭ
    -0.09
    .policy
    -0.08
    íĥķ
    -0.08
    миÑĢ
    -0.08
    åĴĮçĿ¦
    -0.08
    究竣
    -0.08
    Unmarshaller
    -0.08
    .measure
    -0.08
    POSITIVE LOGITS
    ä¼łç»Ł
    0.12
    ä¼łç»ŁçļĦ
    0.10
    æ¡İ
    0.09
    ä¸ĢåĪĩ
    0.09
    ç¹ģçIJIJ
    0.09
     traditional
    0.09
    åĤ³çµ±
    0.09
    æİīäºĨ
    0.09
    çļĦä¸ĢåĪĩ
    0.08
    /mit
    0.08
    Activations Density 0.061%

    No Known Activations