© 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. 13366
    Prev
    Next
    INDEX
    Explanations

    programs and initiatives

    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
    flix
    -0.21
    æĹ¥æĬ¥ç¤¾
    -0.21
    大åĴĸ
    -0.21
    aint
    -0.20
    ายà¸Ļ
    -0.20
    çIJļ
    -0.19
    pseudo
    -0.19
    ä¸Ģé¢Ĺ
    -0.19
    份
    -0.19
    credentials
    -0.18
    POSITIVE LOGITS
     programs
    0.36
     program
    0.31
    å®ŀæĸ½
    0.31
     Programs
    0.29
    programs
    0.29
     programas
    0.29
     initiatives
    0.29
     programmes
    0.29
    计åĪĴ
    0.28
     programa
    0.28
    Activations Density 0.106%

    No Known Activations