© 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. 51796
    Prev
    Next
    INDEX
    Explanations

    member of a family

    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±Ī
    -0.10
    è¯ģåĪ¸æĬķèµĦ
    -0.09
    è°ı
    -0.08
    çļĩå¸Ŀ
    -0.08
    åħ±åĪĽ
    -0.08
    æĶ¿çŃĸæݪæĸ½
    -0.08
    æĢĢ念
    -0.08
    åħµåĻ¨
    -0.08
    å¢ŀåĢ¼
    -0.08
     Associates
    -0.08
    POSITIVE LOGITS
    家åºŃ
    0.16
     families
    0.15
    家æĹı
    0.13
    ä¸ĸ家
    0.13
    ä¸Ģ家
    0.13
     Families
    0.13
    ä¹ĭ家
    0.13
     family
    0.12
     famil
    0.12
    çļĦ家åºŃ
    0.12
    Activations Density 0.107%

    No Known Activations