© 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. 8708
    Prev
    Next
    INDEX
    Explanations

    manner or way

    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
    梯
    -0.10
    yat
    -0.10
    çļĦ巨大
    -0.08
    à¸Ĺร
    -0.08
    åĩºéŨ
    -0.08
    kus
    -0.08
    anta
    -0.08
    еÑĩен
    -0.08
    èĸĦ
    -0.08
    LB
    -0.08
    POSITIVE LOGITS
    çļĦæĸ¹å¼ı
    0.22
    æĸ¹å¼ı
    0.21
     manner
    0.21
     way
    0.21
    è¿Ļç§įæĸ¹å¼ı
    0.19
    æĸ¹å¼ıè¿Ľè¡Į
    0.17
     ways
    0.17
     manière
    0.17
     manera
    0.16
     cách
    0.15
    Activations Density 0.169%

    No Known Activations