© 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. 52071
    Prev
    Next
    INDEX
    Explanations

    power generation and electricity sources

    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
    ç»Ī身
    -0.11
    è°ķ
    -0.10
    é¤
    -0.10
    èĬ
    -0.10
    è¿©
    -0.09
    渤
    -0.09
    åĬłåĽº
    -0.09
    èķ¾
    -0.09
    ä¼¼çļĦ
    -0.09
    åĿļå®ŀ
    -0.08
    POSITIVE LOGITS
    åĤĻ
    0.09
    å¤ĩçĶ¨
    0.09
    ä»ĸèĩªå·±
    0.09
    æĪ¿ä¸ľ
    0.09
     slashes
    0.08
    èµĬ
    0.08
    èĮľ
    0.08
    åħŃåIJĪ
    0.08
     insider
    0.08
    æ®ī
    0.08
    Activations Density 0.070%

    No Known Activations