© 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. 37265
    Prev
    Next
    INDEX
    Explanations

    improve

    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
    æįº
    -0.10
    ä¹°åįķ
    -0.09
    åŃĽ
    -0.09
    elib
    -0.09
    è·¨
    -0.09
    èī²å½©
    -0.09
    人家
    -0.08
    轨
    -0.08
    ther
    -0.08
    åŀĤ
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.09
    æĤłæĤł
    0.09
    æĶ¾å®½
    0.09
    御
    0.09
    Č
    0.08
    åĬŀ好
    0.08
    ä¾Ħ
    0.08
     boss
    0.08
    æĢħ
    0.08
    å·¥ä½ľå²Ĺä½į
    0.08
    Activations Density 0.037%

    No Known Activations