© 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. 17129
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    	TokenName
    -0.21
    ymm
    -0.21
    tractor
    -0.19
     дейÑģÑĤвиÑı
    -0.19
    ObjectId
    -0.18
    æ°Ķ温
    -0.18
    åĩ»
    -0.18
    NSObject
    -0.18
     Bearing
    -0.18
    触
    -0.18
    POSITIVE LOGITS
    èĶ½
    0.22
    æ¯Ķä¾ĭ
    0.20
    bib
    0.18
    æĪIJåĵģ
    0.18
    ish
    0.18
    å©¢
    0.18
    ä¹īåĬ¡
    0.17
    大åıij
    0.17
     reuse
    0.17
    ham
    0.17
    Activations Density 0.003%

    No Known Activations