© 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. 9120
    Prev
    Next
    INDEX
    Explanations

    legal and technical contexts

    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
    ä¼Ĭæĭīåħĭ
    -0.10
    å¾IJå·ŀ
    -0.10
    æĴĤ
    -0.09
    åįĹ京å¸Ĥ
    -0.09
    æ·Ģ
    -0.09
    溧
    -0.09
    éĩįæķ´
    -0.09
    .Attach
    -0.09
    æģº
    -0.09
     Bucc
    -0.08
    POSITIVE LOGITS
     Oregon
    0.15
    Oregon
    0.14
    Portland
    0.13
     Portland
    0.13
    嵩
    0.11
    大çIJĨ
    0.11
    峨
    0.10
     Ghana
    0.10
    èį·
    0.10
    çŃĩ
    0.10
    Activations Density 0.125%

    No Known Activations