© 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. 51999
    Prev
    Next
    INDEX
    Explanations

    sterilizing, rectifying, food, recycling

    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
    湿润
    -0.10
     Porn
    -0.10
    ç²īå°ĺ
    -0.09
    åİĨå¹´
    -0.09
    ä¼łæī¿
    -0.09
    åİĨ
    -0.09
    vet
    -0.09
    俺
    -0.09
    润
    -0.09
    æĮ¯ãĤĬ
    -0.09
    POSITIVE LOGITS
    çķħ
    0.10
    ä¸į失
    0.09
    illin
    0.09
    æŀľæ±ģ
    0.09
    _php
    0.08
    eria
    0.08
    AVA
    0.08
    ä¸ĢèĤ¡
    0.08
    onical
    0.08
    URED
    0.08
    Activations Density 0.126%

    No Known Activations