© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56730
    Prev
    Next
    INDEX
    Explanations

    names of Saints or religious figures

    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
    鹦
    -0.10
    erville
    -0.09
    emet
    -0.09
    ocht
    -0.09
    踱
    -0.09
    ä¿İ
    -0.09
    DataExchange
    -0.09
    çIJ¢ç£¨
    -0.09
    æµĶ
    -0.09
    çĿĢæĢ¥
    -0.08
    POSITIVE LOGITS
    è¤Ĭ
    0.09
    /mock
    0.08
    è¾Ī
    0.08
    å¥Ķ
    0.08
    墨
    0.08
    æĮĸæİĺ
    0.08
     Loose
    0.08
    çıł
    0.08
    å·¨åŀĭ
    0.08
    irl
    0.08
    Activations Density 0.020%

    No Known Activations