© 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. 10848
    Prev
    Next
    INDEX
    Explanations

    technical and scientific abbreviations

    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
     stick
    -0.19
    éĢįéģ¥
    -0.19
     Stick
    -0.19
    墨
    -0.19
    Stick
    -0.19
    Ø´Ùģ
    -0.18
    åIJ¸
    -0.18
     Cabin
    -0.18
    å¹¢
    -0.18
    éĻĦåĬł
    -0.17
    POSITIVE LOGITS
    å±Ĥå±Ĥ
    0.23
    ä¸İåIJ¦
    0.20
     MAKE
    0.20
    å¾Ģäºĭ
    0.20
    缼åħ¸
    0.19
    满èĦ¸
    0.19
    upert
    0.19
    åħļåĴĮåĽ½å®¶
    0.19
    åIJij社ä¼ļ
    0.19
    asan
    0.18
    Activations Density 0.025%

    No Known Activations