© 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. 22520
    Prev
    Next
    INDEX
    Explanations

    different followed by a noun

    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
    ä¸į说
    -0.10
    æĢ§å¼º
    -0.09
     Bucc
    -0.09
    çļĦåīįæıIJä¸ĭ
    -0.09
    ä¸ŃåĽ½çļĦ
    -0.09
    çļĦ缸åħ³
    -0.09
    ä½ı
    -0.09
    éĴµ
    -0.08
    æµİ
    -0.08
    ç½ijéĢļ
    -0.08
    POSITIVE LOGITS
    iable
    0.10
    ä¸ŀ
    0.10
    éħ¿
    0.09
    æľīä¸įåIJĮçļĦ
    0.09
    entially
    0.09
    isti
    0.09
    iated
    0.08
     Pand
    0.08
     sets
    0.08
    bah
    0.08
    Activations Density 0.149%

    No Known Activations