© 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. 15359
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and prepositions

    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
     Schro
    -0.20
    çļĦåij½è¿IJ
    -0.20
    大éĿ¢ç§¯
    -0.19
     Simone
    -0.19
     пÑĢедмеÑĤ
    -0.19
    æĵĤ
    -0.19
    çľ¼åīį
    -0.19
    è±ķ
    -0.18
    ä»Ģä¹Īéĥ½
    -0.18
    çľ¼åīįçļĦ
    -0.18
    POSITIVE LOGITS
    ä¸ĵéŨ
    0.24
    ä¸ĵéĹ¨ä¸º
    0.24
    มาà¸Īาà¸ģ
    0.23
    æĬ½
    0.22
    以åīį
    0.21
    æĽ¾åľ¨
    0.21
    åı¦ä¸Ģä½į
    0.21
    å½ĵåľ°
    0.21
    åĩºèĩª
    0.21
     previous
    0.20
    Activations Density 0.114%

    No Known Activations