© 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. 12599
    Prev
    Next
    INDEX
    Explanations

    parts of a series

    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
    åħ³
    -0.21
    à¸Ħะà¹ģà¸Ļ
    -0.20
    à¸Ħà¸ĵะà¸ģรรม
    -0.20
    eler
    -0.20
     vest
    -0.19
    çļĦçĶŁåij½
    -0.19
    çļĦçĶŁæ´»
    -0.19
    Thought
    -0.19
    æĦıåĽ¾
    -0.19
    æľīçļĦ
    -0.18
    POSITIVE LOGITS
    ä¼ĹæīĢ
    0.20
    æħµ
    0.20
     Wit
    0.19
    decimal
    0.19
    wiÄħzan
    0.18
     fra
    0.18
    ÑĢоÑģ
    0.17
    лÑij
    0.17
    éĺ¶æ¢¯
    0.17
    pora
    0.17
    Activations Density 0.061%

    No Known Activations