© 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. 32836
    Prev
    Next
    INDEX
    Explanations

    church universal

    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
    龸
    -0.09
    浪
    -0.09
    æĢ¥
    -0.09
    æīĵåĩº
    -0.08
    贯彻
    -0.08
    arta
    -0.08
    uos
    -0.08
    çľ¼è§Ĵ
    -0.08
    ika
    -0.08
    æĬµæĬĹ
    -0.08
    POSITIVE LOGITS
    åı¬éĽĨ
    0.10
    åĩĿèģļåĬĽ
    0.10
    inely
    0.09
    cookies
    0.09
    ä»ŀ
    0.09
    éĺĥ
    0.09
    æĽ¦
    0.09
    æ³ģ
    0.09
    figcaption
    0.08
    abel
    0.08
    Activations Density 0.059%

    No Known Activations