© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31141
    Prev
    Next
    INDEX
    Explanations

    aquaculture and fish farming

    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
    ä»»ä½ķæŶåĢĻ
    -0.09
    人æ°Ķ
    -0.09
    ç´«
    -0.08
     wed
    -0.08
    æ´Ĺæīĭ
    -0.08
    绣
    -0.08
    å¸Ń
    -0.08
     fused
    -0.08
    èįī
    -0.08
    fortune
    -0.08
    POSITIVE LOGITS
    çıįçıł
    0.12
     pearls
    0.11
    uki
    0.09
    å½ĵä¹ĭæĹłæĦ§
    0.09
    åħ»æ®ĸ
    0.09
    æ¶Īè´¹åįĩ级
    0.09
    åłª
    0.09
    æĹĭ
    0.09
    天ä¸Ĭ
    0.09
    赡
    0.09
    Activations Density 0.094%

    No Known Activations