© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23816
    Prev
    Next
    INDEX
    Explanations

    environmental emissions and regulations

    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
    å¼Ħ
    -0.10
    åĨ»
    -0.10
    æĭ¿çĿĢ
    -0.09
     Blanch
    -0.09
    æıł
    -0.09
    æĭ¿æĿ¥
    -0.09
    æĭīçĿĢ
    -0.09
     Loot
    -0.09
    å·
    -0.09
     اÙĦبÙĦ
    -0.09
    POSITIVE LOGITS
    没æľīæĥ³åĪ°
    0.09
     Interstate
    0.08
    à¸ļรร
    0.08
    apo
    0.08
    éķķ
    0.08
    unos
    0.08
    ses
    0.08
    ÙĬÙĨا
    0.08
    xmm
    0.08
    æĢ¡
    0.08
    Activations Density 0.051%

    No Known Activations