© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10520
    Prev
    Next
    INDEX
    Explanations

    URL or code snippets

    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
    Negative Logits
    eurs
    -0.19
    plx
    -0.19
    ãĥ¡ãĥ¼ãĤ
    -0.19
    oola
    -0.18
    даÑĩи
    -0.18
    kie
    -0.18
    æĬ½çĥŁ
    -0.18
    çĪ¨
    -0.18
    åıªæĺ¯ä¸ºäºĨ
    -0.18
    oufl
    -0.18
    POSITIVE LOGITS
    äºĭçī©
    0.21
    秽
    0.20
    ä¸İæĹ¶ä¿±è¿Ľ
    0.20
     AnyObject
    0.19
    ç»Ħ建
    0.19
    éĢļè¿ĩ对
    0.19
    Draft
    0.19
    å®ŀçī©
    0.18
     Matters
    0.18
    disk
    0.18
    Activations Density 0.425%

    No Known Activations