© 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. 23782
    Prev
    Next
    INDEX
    Explanations

    meat loaf, writers, lens, deck

    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
    ally
    -0.09
    å½ķçĶ¨
    -0.09
    æݾ
    -0.09
    å§Ķåijĺ
    -0.08
    ante
    -0.08
    oine
    -0.08
    好转
    -0.08
    lix
    -0.08
    ChangedEventArgs
    -0.08
    å¾Ĵ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    (es
    0.09
    busters
    0.09
    ä¹łæĥ¯äºĨ
    0.09
    å½¢
    0.09
    ers
    0.09
    对äºİæĪij们
    0.09
    pipes
    0.09
    ingo
    0.09
    à¹ĥหà¸į
    0.09
    Activations Density 0.002%

    No Known Activations