© 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. 20546
    Prev
    Next
    INDEX
    Explanations

    trigonometric substitution, system icon, tan, one, uninitialised, religious services, in vitro, half

    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
    é©»
    -0.10
    CHO
    -0.09
     using
    -0.09
    ä¸Ńå¤ĸ
    -0.09
    éĩĩçĶ¨äºĨ
    -0.09
    éĩĩçĶ¨
    -0.09
    æĬĬæĮģ
    -0.09
     иÑģполÑĮз
    -0.08
    çݯèĬĤ
    -0.08
    è§Ĩ线
    -0.08
    POSITIVE LOGITS
    çļĦåĬĽéĩı
    0.13
    æĿ¥å½¢å®¹
    0.13
    è¿Ļç§įæĸ¹æ³ķ
    0.13
    æĿ¥åģļ
    0.13
    æĿ¥è¿Ľè¡Į
    0.12
    æĸ¹å¼ıè¿Ľè¡Į
    0.11
    çļĦçľ¼åħī
    0.11
    è¿Ļç§įæĸ¹å¼ı
    0.10
    æĬĢå·§
    0.10
     techniques
    0.10
    Activations Density 0.747%

    No Known Activations