© 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. 13535
    Prev
    Next
    INDEX
    Explanations

    ages and years

    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
    两天
    -0.25
    ä¸ī天
    -0.22
    ä¸Ģ个æĺŁæľŁ
    -0.20
    ä¸Ģ个å°ıæŶ
    -0.20
    åįĬ个æľĪ
    -0.20
    åħģ
    -0.20
    个å¤ļå°ıæŶ
    -0.19
    REN
    -0.19
    ç³»ç»ŁçļĦ
    -0.19
    骡
    -0.19
    POSITIVE LOGITS
    /post
    0.21
    笳
    0.20
     staged
    0.20
     yaÅŁ
    0.20
    (age
    0.20
    离éĢĢä¼ij
    0.20
    人群
    0.19
    opot
    0.19
     age
    0.19
    é²İ
    0.19
    Activations Density 0.079%

    No Known Activations