© 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. 20986
    Prev
    Next
    INDEX
    Explanations

    customer service, technical terms

    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
    å¸
    -0.09
    篾
    -0.08
    å»Ł
    -0.08
    èļĬ
    -0.08
    æĮĤ
    -0.08
    åĴĮä»ĸçļĦ
    -0.08
    ä¼łæĴŃ
    -0.08
    trap
    -0.08
    åºĻ
    -0.08
    亥
    -0.08
    POSITIVE LOGITS
    解çŃĶ
    0.10
    éŨåı£
    0.09
    æĮĩå¼ķ
    0.09
    åıĶåıĶ
    0.09
    è¿Ļ件äºĭæĥħ
    0.09
    å°±é¤IJ
    0.09
     amb
    0.09
    _locator
    0.09
    atha
    0.08
     hum
    0.08
    Activations Density 0.022%

    No Known Activations