© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20866
    Prev
    Next
    INDEX
    Explanations

    under investigation or development

    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
    缴è¾ĸ
    -0.10
    ä¸įå¾Ĺä¸į说
    -0.10
    åŃ£åIJİ
    -0.09
    家ä½ı
    -0.09
    æĮª
    -0.09
    æīĭä¸ĭ
    -0.09
    æĬī
    -0.08
    è¿Ļä¹Īå¤ļ
    -0.08
    è¦ģçľĭ
    -0.08
    ä¸įçĶ±å¾Ĺ
    -0.08
    POSITIVE LOGITS
    æŃ£åľ¨
    0.19
    æŃ£åľ¨è¿Ľè¡Į
    0.18
    缮åīįæŃ£åľ¨
    0.16
    åĬªåĬĽ
    0.15
    ä»įåľ¨
    0.14
     underway
    0.13
     ongoing
    0.13
    ongo
    0.12
    è¿ĺåľ¨
    0.12
    éĥ½åľ¨
    0.11
    Activations Density 0.149%

    No Known Activations