© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31900
    Prev
    Next
    INDEX
    Explanations

    a followed by word

    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
    çıįè´µ
    -0.10
    å¤ļåĬŁèĥ½
    -0.09
    bat
    -0.09
    好æ¶Īæģ¯
    -0.09
    åŃĽ
    -0.08
    cin
    -0.08
    åıĪèĥ½
    -0.08
    诱åıij
    -0.08
     bat
    -0.08
    éĺŁä¼į
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶èĢĮ
    0.11
    çĭIJ
    0.10
    ãģŀ
    0.09
    ÙĪا
    0.09
    æĥĺ
    0.09
    人家
    0.08
     анализ
    0.08
     Gül
    0.08
    空åīį
    0.08
    illion
    0.08
    Activations Density 0.027%

    No Known Activations