© 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. 11236
    Prev
    Next
    INDEX
    Explanations

    lots of

    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
     Entire
    -0.21
    æľĢä¼ĺ
    -0.20
    æĪij们åºĶ该
    -0.19
    ropolitan
    -0.19
    å·¥ä½ľä½ľé£İ
    -0.19
     Cocktail
    -0.19
    ären
    -0.18
    骥
    -0.18
     superiority
    -0.18
    çļĦè·Ŀ离
    -0.17
    POSITIVE LOGITS
     enough
    0.29
    干货
    0.26
    ç»ĨèĬĤ
    0.22
    ино
    0.21
    æĿ¥åĽŀ
    0.20
    çłĶ
    0.20
    åı¯ä¾Ľ
    0.20
    èĬ±èįī
    0.19
    æ§Ĭ
    0.19
    æĸŁ
    0.19
    Activations Density 0.030%

    No Known Activations