© 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. 17093
    Prev
    Next
    INDEX
    Explanations

    speaking conference child health settings

    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
    çī¹åĪ«å£°æĺİ
    -0.22
    åĪ·
    -0.20
    atal
    -0.19
    æŃ£å¦Ĥ
    -0.19
    å½ĵåīįä½įç½®
    -0.19
     ëĺIJ
    -0.18
    æĦŁæŁĵèĢħ
    -0.18
    åıĤèĢĥèµĦæĸĻ
    -0.18
    åľºåĿĩ
    -0.18
    vides
    -0.17
    POSITIVE LOGITS
    ä¸ī代
    0.23
    年人
    0.21
    çĻ¾åĪĨä¹ĭ
    0.20
    åı£è¢ĭ
    0.19
    ä¸īåĪĨ
    0.19
    çĶ·åŃ©åŃIJ
    0.18
     sleeping
    0.18
    æݼ
    0.18
    lös
    0.18
     naked
    0.18
    Activations Density 0.104%

    No Known Activations