© 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. 7838
    Prev
    Next
    INDEX
    Explanations

    measurement of extent or duration

    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
    çĬŁ
    -0.10
    å¾Ĺ天
    -0.10
    flux
    -0.10
     кан
    -0.09
    å§Ĭ
    -0.09
    为é¦ĸ
    -0.09
    pbs
    -0.09
     flux
    -0.09
     Flux
    -0.09
    é«ĺåĩº
    -0.09
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.12
    æķ´ä¸ª
    0.11
    åIJĦè¡Į
    0.11
     entire
    0.11
    èĮĥåĽ´åĨħ
    0.11
     throughout
    0.10
    åħ¨æĸĩ
    0.09
     khắp
    0.09
    çĶ³
    0.09
    ä¸įåģľåľ°
    0.09
    Activations Density 0.280%

    No Known Activations