© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    you receive or obtain

    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
    rst
    -0.20
    æ¡´
    -0.20
    å½¼æѤ
    -0.20
    åľ¨å¤ĸéĿ¢
    -0.19
    ç¯Ŀ
    -0.19
    éŃĶçİĭ
    -0.19
    æŃĩ
    -0.19
    alion
    -0.18
    å¾Īæ¼Ĥ亮
    -0.18
    UNDLE
    -0.18
    POSITIVE LOGITS
    é²ľ
    0.21
    ãĤīãģĦ
    0.20
    诱
    0.20
    AdminController
    0.20
    åī¯æľ¬
    0.19
    æĤ¬æĮĤ
    0.19
    å¯Ŀ
    0.18
    åī¯ä½ľçĶ¨
    0.18
     Irvine
    0.18
    aiser
    0.18
    Activations Density 0.012%

    No Known Activations