© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9086
    Prev
    Next
    INDEX
    Explanations

    Old Testament law and commandments

    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
    åĨ³å®ļ
    -0.10
    èĴ¯
    -0.09
    ames
    -0.08
    åĨµ
    -0.08
    太空
    -0.08
    æī¶
    -0.08
     decide
    -0.08
    çIJĨçͱ
    -0.08
     PS
    -0.08
    å¹²
    -0.07
    POSITIVE LOGITS
    èĩªçĦ¶èĢĮ
    0.12
    å®Ī
    0.11
    å¢Ł
    0.10
    å¼Ľ
    0.10
    å±İ
    0.09
    æĥ©ç½ļ
    0.09
    å»Ł
    0.09
    åĶ¿
    0.09
    uet
    0.09
    icter
    0.09
    Activations Density 0.031%

    No Known Activations