© 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. 11668
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    adies
    -0.23
     BCHP
    -0.23
    	iNdEx
    -0.22
    	RTCT
    -0.21
     Tradable
    -0.21
    ieren
    -0.21
    Pear
    -0.20
    æ¾İ
    -0.20
    æIJ
    -0.20
    éĶĿ
    -0.20
    POSITIVE LOGITS
    æĺ¯æĪijçļĦ
    0.21
    ä¸Ģåı°
    0.21
    ä¸ī次
    0.20
    âĺĵ
    0.20
    æ¢ł
    0.20
    åīŁ
    0.20
    两次
    0.19
    äºĨæĪijçļĦ
    0.19
    è·ijäºĨ
    0.19
    åıĮ
    0.19
    Activations Density 0.091%

    No Known Activations