© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54399
    Prev
    Next
    INDEX
    Explanations

    the definite article

    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
    Ñĥма
    -0.09
    å³Ĵ
    -0.09
    åı¯æĺ¯
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    thouse
    -0.09
    åIJ¬å¾Ĺ
    -0.08
    åıªèĥ½è¯´
    -0.08
    åħ¨äº§ä¸ļéĵ¾
    -0.08
     detriment
    -0.08
    Uvs
    -0.08
    POSITIVE LOGITS
    ä¸ĢåIJį
    0.08
    æѤæĸĩ
    0.08
    inate
    0.08
    æĦĪ
    0.08
    ĶåĽŀ
    0.08
    rame
    0.08
    ç»Ŀ大éĥ¨åĪĨ
    0.08
    åľ¨ç¾İåĽ½
    0.08
    缸è¿ŀ
    0.08
    大éĥ¨åĪĨ
    0.08
    Activations Density 0.337%

    No Known Activations