© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38254
    Prev
    Next
    INDEX
    Explanations

    bombarded, attacked, or overwhelmed

    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
    åįı
    -0.10
    åįĥéĩĮ
    -0.09
    WebKit
    -0.09
     Cassidy
    -0.09
    chester
    -0.09
    ague
    -0.08
    ä¸ĵéĹ¨ä¸º
    -0.08
    å¾Ī
    -0.08
    æĢı
    -0.08
    NST
    -0.08
    POSITIVE LOGITS
    åıĭ
    0.10
    ä¸įåłª
    0.10
    æ¢ħèĬ±
    0.09
    iss
    0.09
     bom
    0.08
    hole
    0.08
    ingly
    0.08
    hard
    0.08
    bug
    0.08
     OP
    0.08
    Activations Density 0.020%

    No Known Activations