© 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. 18637
    Prev
    Next
    INDEX
    Explanations

    suffix of words ending in 'et' or 'ick'

    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
    rim
    -0.10
    æľīæīĢ
    -0.10
    eling
    -0.09
    CDATA
    -0.08
    elong
    -0.08
    çīŁ
    -0.08
    же
    -0.08
    Parms
    -0.08
    quel
    -0.08
    æŁIJä¸Ģ
    -0.08
    POSITIVE LOGITS
    é¼İ
    0.10
    éĽĨåIJĪ
    0.10
    çļĦåIJĪä½ľ
    0.10
    çļĦçݰ象
    0.09
    å¼ĢæĶ¾å¼ı
    0.09
    .xy
    0.09
    éī´
    0.09
    é½IJ
    0.09
    igkeit
    0.09
    ç§ijæķĻ
    0.08
    Activations Density 0.193%

    No Known Activations