© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6814
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions

    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
    æIJŀå¾Ĺ
    -0.11
    ç¼¢
    -0.10
    ä¹°çļĦ
    -0.10
    çħ²
    -0.10
    æīĵå¾Ĺ
    -0.09
    楼主
    -0.09
    æłī
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    ç³Ļ
    -0.09
    éķ¬
    -0.09
    POSITIVE LOGITS
    æĬ¬å¤´
    0.11
    æĬ¬èµ·
    0.11
    æĭ¿èµ·
    0.10
    æĶ¾å¼Ģ
    0.09
    ç´§
    0.09
    æīĭæĮĩ
    0.08
     <![
    0.08
    æĭ¿åĩº
    0.08
    举起
    0.08
    æĬ¬èµ·å¤´
    0.08
    Activations Density 0.034%

    No Known Activations