© 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. 48644
    Prev
    Next
    INDEX
    Explanations

    religious concepts and Christmas

    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
    å·«
    -0.11
    å²±
    -0.09
    æ³¼
    -0.09
    æIJŀ
    -0.09
    pray
    -0.08
    åIJ¹
    -0.08
    åIJĮå¿ĥ
    -0.08
    åij½ä»¤
    -0.08
    令
    -0.08
    æĭĵå±ķ
    -0.08
    POSITIVE LOGITS
    åľ£è¯ŀ
    0.13
    itia
    0.10
    èĥİ
    0.09
    åĶĽ
    0.09
    mouseleave
    0.09
    æĹłå£°
    0.09
    رÙĪÙĨ
    0.09
    .Reverse
    0.08
    InBackground
    0.08
    å±Ī
    0.08
    Activations Density 0.036%

    No Known Activations