© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37397
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs or 'is'/'are'

    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
    å¿ĥæĦ¿
    -0.10
     무ìĬ¨
    -0.09
    æŃ¥è¡Į
    -0.09
     ведÑĮ
    -0.09
    治好
    -0.09
    ResponseBody
    -0.09
    ä¸Ńéĵģ
    -0.08
    è°ģèĥ½
    -0.08
    便æĺ¯
    -0.08
    icare
    -0.08
    POSITIVE LOGITS
    /how
    0.11
    çªģçĦ¶
    0.10
    æĦŁåĪ°
    0.10
    è¿Ļä¹Īåģļ
    0.10
    ä¸įèĥ½
    0.09
    åı«åģļ
    0.09
    è¿Ļä¹Ī说
    0.09
    ä¸įèĥ½åĨį
    0.09
    etter
    0.09
    è¿ĺä¸įæĺ¯
    0.08
    Activations Density 0.082%

    No Known Activations