© 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. 56379
    Prev
    Next
    INDEX
    Explanations

    gerund actions followed by articles or nouns

    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
    é¹ħ
    -0.09
    å¼Ģ
    -0.09
     Rene
    -0.09
    èĬ´
    -0.09
    é¡·
    -0.08
     Drill
    -0.08
    åİħ
    -0.08
    åİ
    -0.08
    纲
    -0.08
    erton
    -0.08
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.11
    å°±æĺ¯è¿Ļæł·
    0.10
    éĢļè¡Į
    0.10
    ä¸įäºĨ
    0.10
    äºĨä»ĸçļĦ
    0.10
    äºĨ个
    0.10
    äºĨä¸įå°ij
    0.09
    ä½ĵä¼ļåĪ°
    0.09
    ãĤ¬ãĤ¤
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    Activations Density 0.106%

    No Known Activations