© 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. 35997
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
    Ñĩем
    -0.10
    èĢĮåıĪ
    -0.10
    ä»ĸèĩªå·±
    -0.09
    ä»ĸçŁ¥éģĵ
    -0.09
    -ren
    -0.09
    ä»ĸè¿ĺ
    -0.09
    èĩ¾
    -0.09
     Rosenstein
    -0.09
    .cgi
    -0.09
    .preview
    -0.09
    POSITIVE LOGITS
     themselves
    0.15
    ä»ĸä»¬åľ¨
    0.13
    ä»ĸ们çļĦ
    0.12
    Their
    0.11
     their
    0.10
    ä»ĸ们æĺ¯
    0.10
    their
    0.09
    eka
    0.09
     Their
    0.09
    ä»ĸ们
    0.09
    Activations Density 0.073%

    No Known Activations