© 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. 20732
    Prev
    Next
    INDEX
    Explanations

    including

    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
    nie
    -0.09
    èIJ¼
    -0.08
    еÑī
    -0.08
    çijķ
    -0.08
    主æĦı
    -0.08
    Ắ
    -0.08
    æ¯ĶåĪ©
    -0.08
    è¿ĽæŃ¥
    -0.07
     oud
    -0.07
    ä»ĩ
    -0.07
    POSITIVE LOGITS
    缮
    0.09
    expo
    0.08
    boro
    0.08
     switch
    0.08
    æıĽ
    0.08
     sach
    0.08
    å¼Ģåıij建设
    0.08
     juni
    0.08
    è¹Ń
    0.08
     JE
    0.08
    Activations Density 0.293%

    No Known Activations