© 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. 36614
    Prev
    Next
    INDEX
    Explanations

    quantifier words followed by 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
    俱
    -0.09
    èıĩ
    -0.09
    ÑĪа
    -0.09
    åŁĤ
    -0.09
    .baseUrl
    -0.08
     Rib
    -0.08
    æĢĴ
    -0.08
    ERP
    -0.08
    弩
    -0.08
    çļĦä¸įåIJĮ
    -0.08
    POSITIVE LOGITS
    æľīäºĽ
    0.12
    ä¸Ģéĥ¨åĪĨ
    0.11
    æľīçļĦ
    0.11
    éĥ¨åĪĨ
    0.10
    æŁIJäºĽ
    0.10
    éĥ¨åĪĨåľ°åĮº
    0.10
    ä¸Ńåįİ
    0.10
    çĶļèĩ³è¿ĺ
    0.10
    大å¤ļæķ°
    0.09
    æŀķ
    0.09
    Activations Density 0.203%

    No Known Activations