© 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. 37058
    Prev
    Next
    INDEX
    Explanations

    authoritative attributions and explanations

    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
    æĸĩä½ĵ
    -0.08
    å°ı
    -0.08
    æ½ľåľ¨
    -0.07
    æĸĩåĮĸ建设
    -0.07
    hack
    -0.07
    asis
    -0.07
     Saturn
    -0.07
    ä¿Ħ
    -0.07
    alia
    -0.07
    çļĦç¡®
    -0.07
    POSITIVE LOGITS
    èijĹ
    0.12
    èijĹä½ľ
    0.12
    æķĻæİĪ
    0.11
    讲座
    0.11
    被èªī为
    0.10
    ä¸»å¼ł
    0.10
    æĮĩåĩº
    0.10
    åľ¨ä»ĸçļĦ
    0.10
    å¼ķé¢Ĩ
    0.10
    åĢ¡å¯¼
    0.09
    Activations Density 0.166%

    No Known Activations