© 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. 19228
    Prev
    Next
    INDEX
    Explanations

    reduce, lower, decrease

    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
    èĶļ
    -0.09
    ÑĢÑĥÑĤ
    -0.08
    iaux
    -0.08
    è¿Ļåıª
    -0.08
    COD
    -0.08
    å¿ħä¸įåı¯å°ij
    -0.08
    ç²ķ
    -0.08
    æľ´å®ŀ
    -0.08
    èĻļå¼±
    -0.08
    éĩijèī²
    -0.08
    POSITIVE LOGITS
    çĦ¶
    0.12
    .Priority
    0.10
    é¦ĸä½į
    0.09
    aye
    0.09
    çĦ¶æĺ¯
    0.09
     trách
    0.09
     Exped
    0.08
    ç¦ģ
    0.08
    åŀĤ
    0.08
    onna
    0.08
    Activations Density 0.005%

    No Known Activations