© 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. 20970
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb/noun

    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
    å¿Ĺ强
    -0.08
    纩
    -0.08
    æĿ¥ä¸įåıĬ
    -0.08
    æĽĪ
    -0.07
    -born
    -0.07
     Ãĺ
    -0.07
    çļĦæľĢåIJİä¸Ģ
    -0.07
    parator
    -0.07
     vice
    -0.07
    åĨįæĿ¥
    -0.07
    POSITIVE LOGITS
    å¹´å¤ľ
    0.10
    çĶļä¹Ī
    0.10
    çķĮéĻIJ
    0.09
    åıijè§ī
    0.09
    åIJĦæł·
    0.09
    çīł
    0.09
    æĶ¯éħį
    0.09
    æıŃéľ²
    0.08
    æİī
    0.08
    æĹ©å·²
    0.08
    Activations Density 0.314%

    No Known Activations