© 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. 20520
    Prev
    Next
    INDEX
    Explanations

    modulation processing, high-speed equipment, heat treatment

    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
    樵
    -0.11
    calar
    -0.10
    ationToken
    -0.09
    ç¼Ĩ
    -0.09
    æĭ®
    -0.09
    eti
    -0.09
    è¿Ļç¯ĩ
    -0.09
     пеÑĢед
    -0.09
    <Result
    -0.08
    IPLE
    -0.08
    POSITIVE LOGITS
    æ·¬
    0.11
    åĨľè´¸
    0.10
    èĬ±çº¹
    0.10
    isure
    0.10
    缮
    0.09
    çĦ¼
    0.09
    çī¹ä»·
    0.09
    轧
    0.09
    çıł
    0.09
     há»ĵi
    0.09
    Activations Density 0.042%

    No Known Activations