© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12326
    Prev
    Next
    INDEX
    Explanations

    we/our followed by auxiliary verbs or 'guys'

    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
    vas
    -0.20
     battleground
    -0.20
    éģĹå¿ĺ
    -0.20
    ä½łä¼ļåıijçİ°
    -0.20
    æĹłç©·
    -0.19
    çļĦåĮºåĪ«
    -0.19
    åIJĦèĩªçļĦ
    -0.19
    åĽ½å®¶æĪĺçķ¥
    -0.18
    åİŁè°ħ
    -0.18
    agle
    -0.18
    POSITIVE LOGITS
    åīįåIJİ
    0.20
     AUD
    0.18
    atically
    0.18
    %E
    0.18
    æķ´ä½ĵ
    0.17
    unday
    0.17
    ignon
    0.17
    好å¤ļ
    0.17
    岸
    0.17
    going
    0.17
    Activations Density 0.012%

    No Known Activations