© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10478
    Prev
    Next
    INDEX
    Explanations

    marshlands and coastal areas

    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
    plit
    -0.10
    ARAM
    -0.09
    éĶĢåĶ®æĶ¶åħ¥
    -0.09
    etta
    -0.09
    elter
    -0.09
    etak
    -0.08
    elem
    -0.08
    è¾¾ä¸įåĪ°
    -0.08
    çļĦäºĭæĥħ
    -0.08
    mare
    -0.08
    POSITIVE LOGITS
    寡
    0.10
    æ²ģ
    0.10
    干线
    0.09
    âĨµ
    0.09
    缺失
    0.09
    æŃ£åĽłä¸º
    0.09
    ÑĮÑıн
    0.09
     cargo
    0.08
    货车
    0.08
    ÑĢова
    0.08
    Activations Density 0.025%

    No Known Activations