© 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. 37331
    Prev
    Next
    INDEX
    Explanations

    chemical industry processes

    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
    æİĮæı¡
    -0.08
    éĻĨ
    -0.08
    dana
    -0.08
    gers
    -0.08
    _nth
    -0.08
    _supported
    -0.08
    åĪĬ
    -0.08
    oron
    -0.08
    æĭį
    -0.08
    istrate
    -0.08
    POSITIVE LOGITS
    åºŁçī©
    0.11
    ä¹ĭ乡
    0.10
    è¡Įä¸ļçļĦ
    0.10
     industry
    0.09
    é¦Ĩ
    0.09
    èģĮä¸ļéģĵå¾·
    0.09
    arrow
    0.09
    è¡Įä¸ļä¸Ń
    0.09
     sector
    0.09
    缮
    0.09
    Activations Density 0.008%

    No Known Activations