© 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. 21154
    Prev
    Next
    INDEX
    Explanations

    vintage items and places

    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
    udas
    -0.09
    ä»ĭ
    -0.09
    ä¸ĢåIJij
    -0.08
    åıĪ好
    -0.08
    åĿĿ
    -0.08
    两åı¥
    -0.08
    ä¸Ģ个æĸ°çļĦ
    -0.08
    åĬ¿
    -0.08
    /Private
    -0.08
     cup
    -0.08
    POSITIVE LOGITS
     ÑģоÑħÑĢани
    0.11
    oldt
    0.10
    old
    0.10
     old
    0.10
    æŧ
    0.10
    çĦķåıij
    0.10
    èĢģ
    0.10
    éģĹçķĻ
    0.09
    OLD
    0.09
     OLD
    0.09
    Activations Density 0.086%

    No Known Activations