© 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. 12343
    Prev
    Next
    INDEX
    Explanations

    presents the verb "is"

    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
    åIJĦæł·
    -0.22
    åĵªäºĽ
    -0.21
    æīĵæŀ¶
    -0.21
    磸
    -0.20
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    -0.19
    總æĺ¯
    -0.19
    ä¹ĭæīĢ以
    -0.19
     Updates
    -0.18
    ãģªãģľ
    -0.18
    ãģłãģĹ
    -0.18
    POSITIVE LOGITS
    个å¤ļ
    0.23
    åĶ±
    0.21
    uth
    0.20
    è·¨è¶Ĭ
    0.20
    æľīæĦıä¹ī
    0.19
    çĩĥ
    0.19
    éĹ´éļĶ
    0.19
     going
    0.19
    æī¾ä¸ª
    0.19
    羣æŃ£
    0.19
    Activations Density 0.034%

    No Known Activations