© 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. 3884
    Prev
    Next
    INDEX
    Explanations

    insects, borers, barks, mines

    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
    鸿
    -0.10
    åģ¶
    -0.09
    潮湿
    -0.09
    èĸ®
    -0.09
     nieu
    -0.09
    rell
    -0.09
     pars
    -0.08
    è¹¼
    -0.08
    è¸ı
    -0.08
    è¸ıå®ŀ
    -0.08
    POSITIVE LOGITS
    é¾Ħ
    0.10
    ests
    0.10
    èł¹
    0.10
    ä¸Ńä¿Ħ
    0.10
    äºĨä¸Ģæī¹
    0.09
    以人为
    0.09
    ColumnType
    0.09
    害
    0.09
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    çĭ¬ä¸ĢæĹłäºĮ
    0.09
    Activations Density 0.080%

    No Known Activations