© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    headlines and titles

    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
    èĢĮ
    -0.21
     so
    -0.20
    ig
    -0.20
    åħ¬å¼Ģ
    -0.19
     considered
    -0.19
     bel
    -0.19
     usual
    -0.19
     irradi
    -0.19
    æīĢ以
    -0.18
     ray
    -0.18
    POSITIVE LOGITS
    å°ıä¼Ļä¼´
    0.24
    ä½ıæĪ¿åħ¬ç§¯
    0.23
    çĶ¨æĪ·æıIJä¾Ľ
    0.21
    è¶Ĭæĺ¯
    0.20
     nrw
    0.20
    åĬŁå¤«
    0.20
    oppable
    0.20
    èĥ½åĬĽå¼º
    0.19
     newcom
    0.19
    æıIJä¾ĽæĽ´å¤ļ
    0.19
    Activations Density 0.069%

    No Known Activations