© 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. 13187
    Prev
    Next
    INDEX
    Explanations

    CD single/version formats

    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
     Illustrated
    -0.21
     Há»ĵ
    -0.19
    ffield
    -0.19
    éĶ¢
    -0.19
     Hawkins
    -0.19
    åŀ¢
    -0.19
     XP
    -0.18
    å»ĵ
    -0.18
    ç§ĺè¯Ģ
    -0.18
    ress
    -0.18
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.30
    æĻļé¤IJ
    0.21
    ä¸¤å¼ł
    0.20
    çļĦè¯Ŀé¢ĺ
    0.20
    ä¸Ĭãģ®
    0.19
    (s
    0.19
    ä¸Ĭæľī
    0.19
    ·æĸ°
    0.19
    /e
    0.19
    ä¸Ģå¼ł
    0.19
    Activations Density 0.009%

    No Known Activations