© 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. 8139
    Prev
    Next
    INDEX
    Explanations

    adoption and adoption-related words

    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
    æ¶ĤæĬ¹
    -0.09
    履约
    -0.09
    Accessible
    -0.08
    èįī
    -0.08
    帽
    -0.08
    inator
    -0.08
    åģľçķĻ
    -0.08
    éĿłçĿĢ
    -0.08
    ãģĦãģŁãĤī
    -0.08
    asan
    -0.08
    POSITIVE LOGITS
     adoption
    0.10
    åѤåĦ¿
    0.10
    秣
    0.10
    èĬĤ
    0.09
    adopt
    0.09
    竦
    0.09
    è·Ľ
    0.09
    èŀŁ
    0.09
     Adopt
    0.09
     Adoption
    0.09
    Activations Density 0.080%

    No Known Activations