© 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. 14091
    Prev
    Next
    INDEX
    Explanations

    planning and organizing

    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
     quá»ijc
    -0.24
    çĽijåIJ¬é¡µéĿ¢
    -0.24
    /animations
    -0.23
    SES
    -0.23
    æĸ°ä¸Ģ代
    -0.22
     Copa
    -0.22
    ZA
    -0.22
    alic
    -0.21
    æĬĢæľ¯æ°´å¹³
    -0.21
     Timeline
    -0.21
    POSITIVE LOGITS
    éķ±
    0.27
    åįĬ天
    0.25
    æ¯ı次éĥ½
    0.24
     Prostitutas
    0.23
     process
    0.23
     Geile
    0.23
     start
    0.23
     мÑıÑģ
    0.23
    æ¯ı天
    0.23
    енно
    0.22
    Activations Density 0.050%

    No Known Activations