© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39194
    Prev
    Next
    INDEX
    Explanations

    regulations

    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
    ë¡Ŀ
    -0.09
    gfx
    -0.09
    aroo
    -0.09
    è¿Ļ对
    -0.08
    å±±åİ¿
    -0.08
    æĸĭ
    -0.08
    å¹¼
    -0.08
    uxtap
    -0.08
     Asi
    -0.08
    踯
    -0.08
    POSITIVE LOGITS
    ally
    0.10
    ج
    0.09
    æīĵçĿĢ
    0.09
    ester
    0.09
    大家åı¯ä»¥
    0.08
    ENTRY
    0.08
    è¡Įäºĭ
    0.08
    鬯
    0.08
    los
    0.08
    ENTER
    0.08
    Activations Density 0.013%

    No Known Activations