© 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. 53107
    Prev
    Next
    INDEX
    Explanations

    ratings or conditions

    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
    æĸ¹éĿ¢çļĦ
    -0.09
    åı¦ä¸Ģè¾¹
    -0.09
    第äºĮæī¹
    -0.09
    ä¹Łæĺ¯å¦ĤæѤ
    -0.09
    åIJĮæł·æĺ¯
    -0.09
    çĶµåŃIJä¿¡æģ¯
    -0.09
    ä¸Ģéĥ¨åĪĨ
    -0.09
    人工
    -0.09
    .dtd
    -0.08
    åľ¬
    -0.08
    POSITIVE LOGITS
    æĦıåij³çĿĢ
    0.10
    æ¿Ĵ
    0.09
    åĨ
    0.09
    oky
    0.09
    ilter
    0.09
     Tul
    0.09
    æªĢ
    0.08
    鸽
    0.08
    åŃļ
    0.08
    代表
    0.08
    Activations Density 0.151%

    No Known Activations