© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15800
    Prev
    Next
    INDEX
    Explanations

    former

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    缮åīį
    -0.24
    第ä¸ī代
    -0.22
     currently
    -0.22
    缮åīį为æŃ¢
    -0.22
    æĸ°çļĦä¸Ģ
    -0.21
    åĪ°æŶåĢĻ
    -0.20
    æĸ°ä¸Ģè½®
    -0.20
    currently
    -0.20
    ели
    -0.19
    åĿĤ
    -0.19
    POSITIVE LOGITS
     bean
    0.20
    å¤ļå¹´çļĦ
    0.19
     rational
    0.19
    ç»Ħç»ĩé¢Ĩ导
    0.18
     stringify
    0.18
    (before
    0.18
    åĮª
    0.18
    è¾īçħĮ
    0.18
    (previous
    0.18
    潦
    0.18
    Activations Density 0.112%

    No Known Activations