© 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. 20715
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns 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
    äºĨæĪijçļĦ
    -0.11
    çIJĨæĥ³çļĦ
    -0.11
    æĸ°çļĦ
    -0.11
    äºĨèĩªå·±çļĦ
    -0.10
    æĸ°çļĦä¸Ģ
    -0.09
    äºĨä¸Ģ个
    -0.09
    went
    -0.09
    好çļĦ
    -0.09
    è¿Ļä¸įæĺ¯
    -0.08
    TextLabel
    -0.08
    POSITIVE LOGITS
    ayne
    0.10
    esser
    0.09
    以åıĬåħ¶ä»ĸ
    0.08
    ¤í
    0.08
    .Editor
    0.08
    igers
    0.08
    Pros
    0.08
    çľ¼éĩĮ
    0.08
    rico
    0.08
    ä½Ī
    0.08
    Activations Density 0.094%

    No Known Activations