© 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. 37379
    Prev
    Next
    INDEX
    Explanations

    dates and deadlines

    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
    æľīè¿ĩ
    -0.09
    å¤ļå¹´
    -0.09
    iek
    -0.09
    andr
    -0.09
    ä»ĩ
    -0.09
    æŶéļĶ
    -0.09
    onium
    -0.08
    âĩ
    -0.08
    èĨı
    -0.08
    uis
    -0.08
    POSITIVE LOGITS
    æĪªæŃ¢
    0.11
    èIJ½
    0.10
    æľŁéĻIJ
    0.10
    溪
    0.10
     deadline
    0.10
    ä»»ä½ķå½¢å¼ı
    0.09
    æŶéĹ´ä¸º
    0.09
    èIJ½åľ°
    0.09
    åIJ¦åĪĻ
    0.09
    lessly
    0.09
    Activations Density 0.025%

    No Known Activations