© 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. 8130
    Prev
    Next
    INDEX
    Explanations

    nutrients, value, crops

    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
    errs
    -0.09
    èĪŀ
    -0.09
    游æĪıæĬĢå·§
    -0.09
    èIJĭ
    -0.09
    èŀŁ
    -0.09
     wireType
    -0.09
    空éĹ´
    -0.08
    å®īå±ħ
    -0.08
    alsex
    -0.08
    èĦ©
    -0.08
    POSITIVE LOGITS
    åł¡åŀĴ
    0.09
    èIJ¥åħ»ä»·åĢ¼
    0.09
    ä¿Ŀåģ¥
    0.08
    èĬĿ麻
    0.08
    æŀľ
    0.08
    é£İæļ´
    0.08
    æĤĦ
    0.08
    utra
    0.08
    楼å®ĩ
    0.08
     fort
    0.08
    Activations Density 0.114%

    No Known Activations