© 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. 13821
    Prev
    Next
    INDEX
    Explanations

    vice president for assistant

    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
    æ¯ģ
    -0.19
     COUR
    -0.19
    æIJĤ
    -0.19
    å½¼æѤ
    -0.18
    åįĥæĸ¹çĻ¾
    -0.18
     grate
    -0.18
    建æĪIJåIJİ
    -0.17
    以æѤ
    -0.17
    åĴĸ
    -0.17
    泫
    -0.17
    POSITIVE LOGITS
    çĽĺçĤ¹
    0.21
    åħ¼
    0.20
     aide
    0.19
    åĸ
    0.19
     Perr
    0.19
    è¿ĺä¸įå¤Ł
    0.18
    æħ°éĹ®
    0.18
    辨åĪ«
    0.18
    çªģåĩºéĹ®é¢ĺ
    0.18
    åIJ«ä¹ī
    0.18
    Activations Density 0.023%

    No Known Activations