© 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. 10549
    Prev
    Next
    INDEX
    Explanations

    I discuss or feel

    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
    饥
    -0.24
    è°ĭ
    -0.23
    arket
    -0.23
    æ¡ħ
    -0.22
    èĢģ头
    -0.22
    æĪIJåIJį
    -0.21
    åij£
    -0.21
    åŁŁ
    -0.21
    éļ¶å±ŀ
    -0.20
    å®ĥçļĦ
    -0.20
    POSITIVE LOGITS
    äºĮèĥİ
    0.23
    æıIJæĹ©
    0.22
    èĢģåħ¬
    0.21
    ä¸Ī夫
    0.21
     Minist
    0.20
    å§IJ妹
    0.20
    åĿļ强
    0.20
    å®īæħ°
    0.19
    ç»ıéªĮ丰å¯Į
    0.19
     medications
    0.19
    Activations Density 0.042%

    No Known Activations