© 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. 8573
    Prev
    Next
    INDEX
    Explanations

    electric and energy related terms

    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
    èĩ»
    -0.09
     pans
    -0.09
    oux
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    åĩºè½¨
    -0.08
    è´Ŀ壳
    -0.08
    coles
    -0.08
    诸èijĽ
    -0.08
    èĮŃ
    -0.08
    éĵ¯
    -0.08
    POSITIVE LOGITS
    æ´»åĬĽ
    0.17
    æĮ¯å¥ĭ
    0.14
    æ´»è·ĥ
    0.13
    活泼
    0.13
    èĥ½éĩı
    0.13
    åħ´å¥ĭ
    0.13
    èĵ¬åĭĥ
    0.13
     excitement
    0.13
    é¼ĵèĪŀ
    0.12
    åĭĥåĭĥ
    0.12
    Activations Density 0.221%

    No Known Activations