© 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. 27878
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions

    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
    åı¯éĢļè¿ĩ
    -0.11
    é©»
    -0.11
    é§IJ
    -0.11
    è¦ģåĿļæĮģ
    -0.10
    åı¯ä»¥éĢļè¿ĩ
    -0.10
     ÐĹна
    -0.10
    è¾¾å°Ķ
    -0.10
    è¾į
    -0.10
    çļĦåıijçĶŁ
    -0.09
    éĥ½ä¸įçŁ¥éģĵ
    -0.09
    POSITIVE LOGITS
    åıijæĮ¥ä½ľçĶ¨
    0.12
    åģļä¸ĢäºĽ
    0.10
    ç¿©
    0.09
    è¿Īåĩº
    0.09
    å±¥è¡Į
    0.09
    被人
    0.08
    enn
    0.08
    è¡Į使
    0.08
    åıĤä¸İåĪ°
    0.08
    ä¸İä¼Ĺä¸įåIJĮ
    0.08
    Activations Density 0.041%

    No Known Activations