© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12913
    Prev
    Next
    INDEX
    Explanations

    effectively / essentially followed by action

    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
    åĢ¼å¾Ĺ
    -0.23
    çī¹ãģ«
    -0.22
    å¥ijæľº
    -0.20
    è¡·å¿ĥ
    -0.19
    çī¹åĪ«æĺ¯
    -0.18
     besonders
    -0.18
     especialmente
    -0.18
    åı¯èĥ½æĺ¯
    -0.17
    åĢ¼å¾Ĺåħ³æ³¨
    -0.17
    xious
    -0.17
    POSITIVE LOGITS
    缸å½ĵäºİ
    0.31
    -minded
    0.24
     effectively
    0.22
    åįĬ个
    0.21
    鼶è·Ŀ离
    0.21
    éļIJå½¢
    0.21
     essentially
    0.21
     equivalent
    0.21
    éļIJ
    0.20
    åŁĭ
    0.19
    Activations Density 0.025%

    No Known Activations