© 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. 10443
    Prev
    Next
    INDEX
    Explanations

    ’s, is, 'll, are, can

    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
    ous
    -0.20
    edException
    -0.20
     conveyed
    -0.19
     plank
    -0.19
    çĶŃ
    -0.18
     adj
    -0.18
     mil
    -0.18
     either
    -0.18
    ä½ķå¤Ħ
    -0.18
    ãĤĵãģ§ãģĻãĤĪãģŃ
    -0.17
    POSITIVE LOGITS
    è¿Ļ份
    0.24
    è¿Ļ个éĹ®é¢ĺ
    0.24
    æĸ¹éĿ¢çļĦ
    0.23
    åĮĸè¿Ľç¨ĭ
    0.22
    ä¸Ģ份
    0.21
    è¿Ļ对äºİ
    0.21
    éłħ
    0.20
    éĥ¨ä»½
    0.19
    MUX
    0.18
    çļĦä¸ĢäºĽ
    0.18
    Activations Density 0.018%

    No Known Activations