© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37799
    Prev
    Next
    INDEX
    Explanations

    born and son

    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
    èī¯å¿ĥ
    -0.10
    éĻĽ
    -0.10
     kn
    -0.09
    è¿ĩåİ»
    -0.08
    hoff
    -0.08
    æѤåĪ»
    -0.08
    é£ŁåłĤ
    -0.08
     Kn
    -0.08
    äºĴ
    -0.08
    è¿Ľè´§
    -0.08
    POSITIVE LOGITS
    ä»İå°ıå°±
    0.12
    åĩºçĶŁäºİ
    0.10
    æľī两个
    0.10
    åĩºèº«
    0.10
    æĺ¯ä¸ª
    0.10
    ç®Ĺæĺ¯
    0.10
    ä¸ĸ家
    0.10
    天èµĭ
    0.10
    æľīæĿĥ
    0.09
    èIJ¼
    0.09
    Activations Density 0.507%

    No Known Activations