© 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. 36650
    Prev
    Next
    INDEX
    Explanations

    Tyson

    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
    äºĨèĩªå·±çļĦ
    -0.09
    å®ļåIJij
    -0.09
    ç»Ħç»ĩå®ŀæĸ½
    -0.09
    oral
    -0.09
     MAD
    -0.08
    æݪ
    -0.08
    aret
    -0.08
    建设çĶ¨åľ°
    -0.08
     ÄIJá»ĭa
    -0.08
     coli
    -0.08
    POSITIVE LOGITS
    æ¯ĭ
    0.10
    omic
    0.09
    ettel
    0.09
    ä¸Ńåħ³
    0.09
    ä¸¥æł¼çļĦ
    0.09
     Rift
    0.09
    åŃĽ
    0.09
    евиÑĩ
    0.08
    kle
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
    Activations Density 0.001%

    No Known Activations