© 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. 13825
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     whip
    -0.23
    代
    -0.21
    å¾Ĵ
    -0.19
    omes
    -0.18
    èļ¤
    -0.18
     Hipp
    -0.18
    .TEST
    -0.18
    CTest
    -0.17
    鸳
    -0.17
    _CHAN
    -0.17
    POSITIVE LOGITS
    éŁª
    0.22
    ç¥ŀå·ŀ
    0.20
    ва
    0.20
    dbuf
    0.18
    æĨ©
    0.18
    çĶ¸
    0.18
    avia
    0.18
    å¾Ĺå¾Ī好
    0.18
    åľ¨åŃ¦æł¡
    0.17
     MSR
    0.17
    Activations Density 0.000%

    No Known Activations