© 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. 55036
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
    ipop
    -0.10
    éĺ²å¾¡
    -0.10
    iaux
    -0.09
    Ath
    -0.09
    æĻ®åıĬ
    -0.09
    nell
    -0.09
    æģ¬
    -0.09
    éĤ£ä¸ªäºº
    -0.09
    翼
    -0.09
     Defensive
    -0.09
    POSITIVE LOGITS
    对æѤ
    0.09
     favourite
    0.08
    è¿«
    0.08
    éĹ²ç½®
    0.08
    orge
    0.08
    åĪģ
    0.08
    ç¬Ļ
    0.08
    æĿ¾
    0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    0.07
    åħ¥åºĵ
    0.07
    Activations Density 0.123%

    No Known Activations