© 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. 7771
    Prev
    Next
    INDEX
    Explanations

    Raymond or Ray

    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
    iate
    -0.09
    åĭĥåĭĥ
    -0.09
    ëĿ¼ëıĦ
    -0.09
    áŁĴáŀ
    -0.09
    ·
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    olic
    -0.08
    anger
    -0.08
    icom
    -0.08
    åĩıæİĴ
    -0.08
    POSITIVE LOGITS
    fully
    0.13
    edly
    0.13
    -eyed
    0.10
    çħ
    0.10
    uest
    0.09
    icals
    0.09
    bearer
    0.09
    mare
    0.09
    ulet
    0.09
    åħ¶æīĢ
    0.09
    Activations Density 0.066%

    No Known Activations