© 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. 37466
    Prev
    Next
    INDEX
    Explanations

    expressed bylicensed tolicensed under

    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
    ç°ĭ
    -0.10
    omat
    -0.08
    æı¡
    -0.08
    çĿĢçľ¼äºİ
    -0.08
    ä¼ļéķ¿
    -0.08
    æĪĴ
    -0.08
    less
    -0.08
    é©°æı´
    -0.08
     Newark
    -0.08
    æĮ¤
    -0.08
    POSITIVE LOGITS
    ç½²
    0.09
    ×ŀ×ij
    0.09
    Runnable
    0.09
    éļ½
    0.09
    åı°ä¸Ĭ
    0.08
    颢
    0.08
    å¸ħ
    0.08
    ertia
    0.08
     Disposable
    0.08
    ãĤ¿ãĤ¤
    0.08
    Activations Density 0.015%

    No Known Activations