© 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. 11423
    Prev
    Next
    INDEX
    Explanations

    action after certain words

    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
    idget
    -0.23
    	RTLR
    -0.22
    HeaderCode
    -0.21
    æĥ³è¿ĩ
    -0.21
    \\/
    -0.21
    åŃIJå¼Ł
    -0.21
    ìĸ»
    -0.20
    çĶŁæ´»æ°´å¹³
    -0.20
    .AWS
    -0.19
    UTILITY
    -0.19
    POSITIVE LOGITS
    èĩªåĬ¨
    0.30
    é»ĺ认
    0.28
    æĺ¾ç¤º
    0.28
    æıIJ示
    0.28
     itself
    0.27
    è¯ĨåĪ«
    0.27
    èĩªåĭķ
    0.26
     automatically
    0.26
    æľ¬èº«
    0.24
     default
    0.24
    Activations Density 0.351%

    No Known Activations