© 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. 16570
    Prev
    Next
    INDEX
    Explanations

    when was the last time

    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
    è¿Ļæīįæĺ¯
    -0.23
     Essentials
    -0.21
     FIXED
    -0.20
     Crest
    -0.20
     Fixed
    -0.19
    åīįæľŁ
    -0.19
    ä¸Ģè´¯
    -0.19
    æĪij个人
    -0.18
    çļĦæķ´ä½ĵ
    -0.18
    åħ¶ä»ĸçļĦ
    -0.18
    POSITIVE LOGITS
    èĦį
    0.21
    çªĪ
    0.21
    诵
    0.20
    çĶ¨æĿ¥
    0.19
    ä¸Ģéĥ¨
    0.19
    ä¸ĸçķĮä¸ĬæľĢ
    0.19
    rett
    0.18
    éĤ£ä½ł
    0.18
    æ²īæµ¸åľ¨
    0.18
     resort
    0.18
    Activations Density 0.172%

    No Known Activations