© 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. 37239
    Prev
    Next
    INDEX
    Explanations

    `coding=utf-8` or score `reaches`

    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
    ä¸įè¿ľ
    -0.08
    å¥ĩå¹»
    -0.08
    æ°ijåĬŀ
    -0.08
    çļĵ
    -0.08
     kits
    -0.07
    зван
    -0.07
    å¾Ģ
    -0.07
    textInput
    -0.07
    äºĽ
    -0.07
    æ³ĵ
    -0.07
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.09
    é¢ī
    0.09
    æķ¢äºİ
    0.09
    åįģä¸ĩ
    0.09
    uptime
    0.09
    .Must
    0.08
     nors
    0.08
    åĭĩäºİ
    0.08
    ophobia
    0.08
    åıĬ以ä¸Ĭ
    0.08
    Activations Density 0.021%

    No Known Activations