© 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. 17775
    Prev
    Next
    INDEX
    Explanations

    Saint figures or religious art

    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
    .opensource
    -0.10
    ideo
    -0.09
    æł·åŃIJ
    -0.09
    å½±éŁ³
    -0.09
    æŁĦ
    -0.09
    é£İéĩĩ
    -0.09
    .ua
    -0.09
     pictures
    -0.09
    è§ĨåIJ¬
    -0.09
    èĥļ
    -0.09
    POSITIVE LOGITS
    viewer
    0.11
     foreground
    0.10
    读èĢħ
    0.10
    Foreground
    0.09
     viewer
    0.09
     zosta
    0.08
     adul
    0.08
    دÙĬÙĨ
    0.08
     viewers
    0.08
    foreground
    0.08
    Activations Density 0.041%

    No Known Activations