© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    TOP SECRET

    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
    ese
    -0.22
    tery
    -0.21
    Aqu
    -0.20
    apor
    -0.18
    ulti
    -0.18
     Says
    -0.18
    rab
    -0.18
     affairs
    -0.18
    Assistant
    -0.18
    å¤ļ人
    -0.18
    POSITIVE LOGITS
    éĬ®
    0.25
    å¨Ī
    0.22
    æĪIJé¾Ļ
    0.21
    åѦåĪ°
    0.21
    ä¼ļå±ķ
    0.20
    ĶåĽŀ
    0.20
    ä¿Ŀæ´ģ
    0.19
    =top
    0.19
    顶éĥ¨
    0.19
    æĮ¹
    0.19
    Activations Density 0.058%

    No Known Activations