© 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. 1901
    Prev
    Next
    INDEX
    Explanations

    British Empire or French Revolution

    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
    æĬĹæĪĺ
    -0.09
    ses
    -0.09
    满æĦıçļĦ
    -0.09
    RLF
    -0.09
    æĩĴ
    -0.08
    eds
    -0.08
    incare
    -0.08
    å°ķ
    -0.08
     cellul
    -0.08
    abad
    -0.08
    POSITIVE LOGITS
     superst
    0.10
    å´ĩæĭľ
    0.09
     Jupiter
    0.09
     Phill
    0.09
    PELL
    0.08
     super
    0.08
     sne
    0.08
    bris
    0.08
    æīĵåIJ¬
    0.08
     ende
    0.08
    Activations Density 0.230%

    No Known Activations