© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12616
    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
    esco
    -0.20
    ä¸ĩéĩĮ
    -0.19
    ç¼Ģ
    -0.18
    lined
    -0.18
    åłµ
    -0.18
    rough
    -0.17
    ough
    -0.17
     SERIES
    -0.17
    uled
    -0.17
    chu
    -0.17
    POSITIVE LOGITS
    çĦ¶
    0.22
    æ¯ı人
    0.19
    ç¢Į
    0.18
    æ´»åĬĽ
    0.18
    çŃĭ
    0.18
     моÑī
    0.17
    ä¾ĭå¤ĸ
    0.17
    å¤ļå°ij
    0.17
     upon
    0.17
    京津
    0.17
    Activations Density 0.000%

    No Known Activations