© 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. 56083
    Prev
    Next
    INDEX
    Explanations

    mutual reciprocity

    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
    鬯
    -0.09
    亡
    -0.09
    rat
    -0.08
    èĤĩ
    -0.08
    å¾ĹäºĨ
    -0.08
    è¿Ļäºĭ
    -0.08
    åijĹ
    -0.08
    ä¸¤å¼ł
    -0.08
    æĶ¾å¼ĥ
    -0.08
    irc
    -0.08
    POSITIVE LOGITS
    å½¼æѤ
    0.25
    äºĴ缸
    0.19
    缸äºĴ
    0.19
     mutual
    0.13
    ãģĬäºĴãģĦ
    0.12
     elkaar
    0.12
     Mutual
    0.12
     ìĦľë¡ľ
    0.11
    åIJĦèĩª
    0.11
     mutually
    0.11
    Activations Density 0.078%

    No Known Activations