© 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. 38464
    Prev
    Next
    INDEX
    Explanations

    stories continue narratives

    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
    ç½ij讯
    -0.10
    æѤæĸĩ
    -0.09
    åIJĦ级
    -0.08
    æĺĶ
    -0.08
    #line
    -0.08
     undue
    -0.08
    æ³£
    -0.08
    æķıéĶIJ
    -0.08
    æĤłä¹ħ
    -0.08
    åĩºèº«
    -0.08
    POSITIVE LOGITS
    继ç»Ń
    0.15
    åĨį次
    0.12
    æĸ°çļĦ
    0.11
    å·©åĽº
    0.11
    ä»įæľª
    0.11
    继ç»Ńä¿ĿæĮģ
    0.11
     again
    0.11
    åıĪä¸Ģ次
    0.11
     continued
    0.11
    è¿Ľä¸ĢæŃ¥
    0.11
    Activations Density 0.222%

    No Known Activations