© 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. 17116
    Prev
    Next
    INDEX
    Explanations

    search form, search this blog

    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
    ç«ĭ
    -0.23
    èĩªæĿ¥
    -0.21
    æĶ¾å¿ĥ
    -0.20
    åĬ©
    -0.20
    便
    -0.19
    èİ«
    -0.19
    飧
    -0.19
    çķĮçļĦ
    -0.19
    ä¹Łå°±æĺ¯
    -0.18
    æĢģ
    -0.18
    POSITIVE LOGITS
    sortBy
    0.21
    åı£å¾Ħ
    0.20
    èĥ¸æĢĢ
    0.20
    æ²»çIJĨä½ĵç³»
    0.19
    SOAP
    0.19
     Globe
    0.18
    Anywhere
    0.18
    	search
    0.18
    å¹´åĨħ
    0.18
    _lv
    0.18
    Activations Density 0.008%

    No Known Activations