© 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. 8833
    Prev
    Next
    INDEX
    Explanations

    no matter

    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
    UNS
    -0.09
     primary
    -0.09
    ads
    -0.09
    好ä¸į容æĺĵ
    -0.09
    å¿ĥæĢģ
    -0.09
    ucci
    -0.09
     dou
    -0.08
    åĶ¯ä¸ĢçļĦ
    -0.08
    ç¥ĸçĪ¶
    -0.08
    redis
    -0.08
    POSITIVE LOGITS
    人éĥ½
    0.13
    orno
    0.12
    theless
    0.12
     ìĤ¬ëŀĮìĿĢ
    0.11
    å¹´é¾Ħ段
    0.10
    ä¼ģä¸ļåľ¨
    0.10
    äººåľ¨
    0.10
    åIJ¬è¯´è¿ĩ
    0.10
    æĺ¯ä¸ºäºĨ
    0.10
    人ãģ¯
    0.09
    Activations Density 0.043%

    No Known Activations