© 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. 13380
    Prev
    Next
    INDEX
    Explanations

    could be

    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
    лов
    -0.21
    æĪijçĽ¸ä¿¡
    -0.20
    å¾ģ
    -0.19
    psc
    -0.19
    ë§IJ
    -0.19
    尽快
    -0.18
    åıĸè¯ģ
    -0.18
    uchs
    -0.18
    为åĩĨ
    -0.18
    ÙģØ©
    -0.18
    POSITIVE LOGITS
     apparently
    0.24
     evidently
    0.23
     Apparently
    0.23
    QUIRES
    0.22
    çľĭæĿ¥
    0.22
    æŀľçĦ¶
    0.21
    æŀľ
    0.21
     hindsight
    0.21
    åį³ä¾¿
    0.20
    æĺ¯å¤ļä¹Ī
    0.20
    Activations Density 0.189%

    No Known Activations