© 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. 20503
    Prev
    Next
    INDEX
    Explanations

    of the season

    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
    à¦ĵ
    -0.10
     Cary
    -0.09
    ento
    -0.09
    æ¯ıå¹´éĥ½
    -0.09
    uet
    -0.08
    ancial
    -0.08
    èģĶç³»æĸ¹å¼ı
    -0.08
    .Keys
    -0.08
    éĩĬ
    -0.08
    å¡ŀ
    -0.08
    POSITIVE LOGITS
    å±¥
    0.09
     blindness
    0.08
    hamster
    0.08
    æijĺ
    0.08
    AdapterFactory
    0.08
    ATS
    0.08
    潦
    0.08
    ä¸Ń举
    0.08
     hypers
    0.08
    dag
    0.08
    Activations Density 0.006%

    No Known Activations