© 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. 17005
    Prev
    Next
    INDEX
    Explanations

    calling someone

    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
    ç¥Ģ
    -0.21
    trä
    -0.18
    ós
    -0.17
     lur
    -0.17
     trúc
    -0.17
    cup
    -0.17
     pena
    -0.17
    è¦ĭãģĪ
    -0.16
     Ñģобой
    -0.16
    å¾ľ
    -0.16
    POSITIVE LOGITS
    çĶµè¯Ŀ
    0.29
    âĺİ
    0.26
    oused
    0.26
    igraphy
    0.25
    звон
    0.25
    åı·çłģ
    0.25
    éĽ»è©±
    0.24
     ÑĤелеÑĦон
    0.23
     telefon
    0.23
     phone
    0.22
    Activations Density 0.030%

    No Known Activations