© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17261
    Prev
    Next
    INDEX
    Explanations

    following "to" or "for"

    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
    Negative Logits
    åĽ½å®¶æĪĺçķ¥
    -0.20
    鸳
    -0.19
    åľ¨æĪijçļĦ
    -0.17
    建åĨĽ
    -0.17
     ft
    -0.17
    ä¸ĢèĪ¬çļĦ
    -0.17
    ç©¿è¿ĩ
    -0.17
    ä»Ģ
    -0.17
    ig
    -0.17
    äºļè¿IJä¼ļ
    -0.17
    POSITIVE LOGITS
    使åħ¶
    0.26
    OTES
    0.24
    使ä¹ĭ
    0.21
    为åħ¶
    0.20
    tas
    0.18
    StateMachine
    0.18
    gem
    0.18
    untime
    0.17
    让å®ĥ
    0.17
    agram
    0.17
    Activations Density 1.191%

    No Known Activations