© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47580
    Prev
    Next
    INDEX
    Explanations

    to + imperative verb

    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
    Negative Logits
    ked
    -0.09
    PEAR
    -0.09
    绶
    -0.09
    人士
    -0.09
    Disclaimer
    -0.09
    åŀĴ
    -0.08
    ä¸ĢæĶ¯
    -0.08
    ä¸Ńå±±
    -0.08
    éħĮ
    -0.08
    оÑī
    -0.08
    POSITIVE LOGITS
    ãģĵãģĿ
    0.09
     expect
    0.09
    ocus
    0.09
     fiat
    0.09
     stakes
    0.09
     Closed
    0.08
    çĽ¸ä¿¡
    0.08
    emic
    0.08
    ä¸ľè¥¿
    0.08
    ä¼łçľŁ
    0.08
    Activations Density 0.021%

    No Known Activations