© 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. 30790
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    ä¹ĥæĺ¯
    -0.11
    è¿ĺæĥ³
    -0.11
    avery
    -0.09
    olest
    -0.09
    _cleanup
    -0.08
    æģ¯æģ¯
    -0.08
    å¼ij
    -0.08
    è¿ĺæľīä¸Ģ个
    -0.08
    æľĢè¿ij
    -0.08
    ä»Ĭ天
    -0.08
    POSITIVE LOGITS
    ç»ıæŁ¥
    0.10
    åıĺå¾Ĺ
    0.09
    å·¥ä¸ļåĽŃåĮº
    0.09
    å°±æĪIJäºĨ
    0.09
    éĺ²çº¿
    0.09
    semble
    0.09
    å°±å¼Ģå§ĭ
    0.09
    工夫
    0.09
    åıĺå¾ĹæĽ´åĬł
    0.09
    ä¸ĢèĤ¡
    0.09
    Activations Density 0.079%

    No Known Activations