© 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. 52016
    Prev
    Next
    INDEX
    Explanations

    government and ceasefire deals

    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
     ЮÑĢ
    -0.10
    otron
    -0.10
     Sommer
    -0.09
    MainFrame
    -0.09
    å´ĩæĭľ
    -0.09
    aned
    -0.09
    _MEM
    -0.09
    åĬłå¤§
    -0.09
    åĬ³åĬ¡
    -0.09
    æĥ¹
    -0.09
    POSITIVE LOGITS
    è°ĪåĪ¤
    0.12
     talks
    0.11
    è£Ĥ
    0.09
    æģ¢å¤į
    0.09
    è¿Ľç¨ĭ
    0.09
    è¿ĩ渡
    0.09
    è°Īè°Ī
    0.09
     resolution
    0.09
    æļ´åĬĽ
    0.09
     talk
    0.09
    Activations Density 0.097%

    No Known Activations