© 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. 36779
    Prev
    Next
    INDEX
    Explanations

    before followed by verb

    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
    .nl
    -0.10
    è¿Ļè¯Ŀ
    -0.09
    æĪĸåħ¶ä»ĸ
    -0.09
    以åıĬåħ¶ä»ĸ
    -0.09
     ØŃÙĬÙĨ
    -0.09
    arness
    -0.09
    æĪĸèĢħæĺ¯
    -0.09
    å¦Ĥæŀľè¯´
    -0.09
    èĻ½çĦ¶
    -0.09
    èĻ½çĦ¶æĺ¯
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.08
    AttributeValue
    0.08
    æŁ¬
    0.08
    åıijå±ķ空éĹ´
    0.08
     eventually
    0.08
    Recognizer
    0.08
    æľįåĬ¡äºİ
    0.08
    说æĺ¯
    0.08
    åºĶæľīçļĦ
    0.08
    æľīä¸įåIJĮçļĦ
    0.08
    Activations Density 0.030%

    No Known Activations