© 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. 16959
    Prev
    Next
    INDEX
    Explanations

    wrong or right

    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
    å°ıåŀĭ
    -0.23
    æĢĿèĢĥ
    -0.21
    追éĹ®
    -0.20
    éļ¶å±ŀäºİ
    -0.18
    åĮĻ
    -0.18
    mare
    -0.18
    ought
    -0.18
    å®ŀä¹ł
    -0.17
    æľ¬èº«å°±
    -0.17
    æĢĿç´¢
    -0.17
    POSITIVE LOGITS
    åħ³äºİ
    0.21
    没éĶĻ
    0.20
     regarding
    0.19
     Aires
    0.19
    è¯ŀ
    0.19
    oka
    0.19
     about
    0.18
    è·µ
    0.18
    ares
    0.18
    akah
    0.18
    Activations Density 0.031%

    No Known Activations