© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17160
    Prev
    Next
    INDEX
    Explanations

    related to digital artifacts, files, or data

    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
    Negative Logits
    È®
    -0.20
    éĤ£è¾¹
    -0.20
    åĮ»ç§ij
    -0.20
    åīįåĩłå¹´
    -0.19
    ä»ĸå¦Ī
    -0.19
    ï¼
    -0.19
     lat
    -0.19
    æģ¨ä¸įå¾Ĺ
    -0.19
    ãģĭãģ£ãģŁãģ§ãģĻ
    -0.19
    ÙħÙģاÙĪضات
    -0.19
    POSITIVE LOGITS
    Sir
    0.22
    olia
    0.19
    é¼ĵèĪŀ
    0.19
    _entry
    0.18
    UCE
    0.18
    çĨł
    0.18
    å¨ĺå¨ĺ
    0.17
    жи
    0.17
    rais
    0.17
    éĻ¤å¤ķ
    0.17
    Activations Density 0.314%

    No Known Activations