© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    Intel architecture and assembly

    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
    ç¼ļ
    -0.23
    ä¸Ģæĸ¹
    -0.21
    åĴĸ
    -0.19
    æĭīæĸ¯
    -0.19
    igid
    -0.19
    ç¡IJ
    -0.19
    麾
    -0.18
    à¹Īà¸Ńà¸ĩ
    -0.18
    éħª
    -0.18
    èĥ¶åĽĬ
    -0.18
    POSITIVE LOGITS
     Crimson
    0.23
    å®ļå¾ĭ
    0.22
     Intel
    0.21
    ä½ĵ温
    0.21
     Prescott
    0.21
     laptops
    0.21
     Competitive
    0.20
    èĭ»
    0.20
     chip
    0.20
     ACPI
    0.19
    Activations Density 0.127%

    No Known Activations