© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19557
    Prev
    Next
    INDEX
    Explanations

    newsletters, editions, or newsletters

    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
    marvin
    -0.11
    å±į
    -0.10
    社ä¼ļåĮĸ
    -0.09
     pans
    -0.09
    anse
    -0.09
    驼
    -0.09
    主æĿĥ
    -0.09
    ç¾Ĭæ¯Ľ
    -0.09
    _VIEW
    -0.08
    omatic
    -0.08
    POSITIVE LOGITS
     scrap
    0.10
    ç§ijæĻ®
    0.10
    ä¸Ģè§Ĵ
    0.09
    ä¸ĢæľŁ
    0.09
    åľ¨è·¯ä¸Ĭ
    0.09
    å®ŀæĸ½ç»ĨåĪĻ
    0.08
    书éĿ¢
    0.08
    åĪ¶ä½ľ
    0.08
    ä¸įåģľçļĦ
    0.08
    èĥ½å¾ĹåĪ°
    0.08
    Activations Density 0.056%

    No Known Activations