© 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. 16695
    Prev
    Next
    INDEX
    Explanations

    define statements

    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
    å½ĵçĦ¶æĺ¯
    -0.23
    åīª
    -0.19
    åį´åıĪ
    -0.19
    çĿ«
    -0.19
    çijĦ
    -0.18
    çī¹åĪ«æĺ¯
    -0.18
    Anim
    -0.18
    resses
    -0.18
    ASTE
    -0.18
    å°¤åħ¶æĺ¯
    -0.17
    POSITIVE LOGITS
    éĹ´æİ¥
    0.23
    è¾ĩ
    0.21
    以å¾Į
    0.19
    ä»Ģä¹ĪæĦıæĢĿ
    0.18
     Cary
    0.18
    æĦıæĢĿæĺ¯
    0.18
    å·§å¦Ļ
    0.17
    æĬĢå·§
    0.17
     Null
    0.17
    ungle
    0.17
    Activations Density 0.703%

    No Known Activations