© 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. 38937
    Prev
    Next
    INDEX
    Explanations

    oxidation and Fenton chemistry

    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
    æĭ¿äºĨ
    -0.10
    åŃ¦æł¡çļĦ
    -0.09
    ä¸Ńè¶ħ
    -0.09
    à´«
    -0.09
    寡
    -0.09
    æ¼ı
    -0.09
    odian
    -0.09
    èĢģ乡
    -0.08
    人人éĥ½
    -0.08
    ä¸įåIJĪ
    -0.08
    POSITIVE LOGITS
    çŁ³å¤´
    0.09
    å²IJ
    0.09
    åıįå¤į
    0.09
    箧
    0.09
    _HW
    0.08
    æĦ
    0.08
    èĵĦ
    0.08
     break
    0.08
    åĪĨ解
    0.08
    lyn
    0.08
    Activations Density 0.290%

    No Known Activations