© 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. 9096
    Prev
    Next
    INDEX
    Explanations

    new versions

    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
    åŀĤ
    -0.09
    _ALREADY
    -0.09
     rah
    -0.09
    æĵļ
    -0.08
    æį®
    -0.08
    æĸĩ书
    -0.08
     Tall
    -0.08
    èĩĬ
    -0.08
    伶
    -0.08
    \DependencyInjection
    -0.08
    POSITIVE LOGITS
    è¿Ļç±»
    0.14
    æĻ®åıĬ
    0.12
    å¸ĤéĿ¢ä¸Ĭ
    0.11
    款å¼ı
    0.10
    主æµģ
    0.10
    çݰ代
    0.10
    æѤ类
    0.10
    ä¸ĢèĪ¬éĥ½æĺ¯
    0.10
    è´Ńä¹°
    0.09
    å®ĥ们
    0.09
    Activations Density 0.201%

    No Known Activations