© 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. 10434
    Prev
    Next
    INDEX
    Explanations

    atonement, sins, forgiveness

    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
    é«ĺæīĭ
    -0.29
    åħ±åĴĮåĽ½
    -0.20
    åĬŁ
    -0.19
    éħĮ
    -0.19
    æĹıèĩªæ²»
    -0.18
    ç´¢åıĸ
    -0.18
    çĶ¨å¿ĥ
    -0.17
    á»īnh
    -0.17
    è©¢
    -0.17
    urally
    -0.17
    POSITIVE LOGITS
    ä¸įäºĨ
    0.23
    èµİ
    0.19
    TEE
    0.19
    bw
    0.19
    ç¥ĵ
    0.18
    tal
    0.18
    æ¸ħéĻ¤
    0.18
     lá»Ĺi
    0.17
    äºĨä»ĸçļĦ
    0.17
    ç§ijæĬĢèĤ¡ä»½
    0.17
    Activations Density 0.005%

    No Known Activations