© 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. 10408
    Prev
    Next
    INDEX
    Explanations

    APR, rms, Y

    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
    iku
    -0.19
    éĿ¢ç²ī
    -0.19
     Tough
    -0.18
    spo
    -0.18
    ioc
    -0.18
     GiriÅŁ
    -0.18
     Orth
    -0.18
    å©Ĩ
    -0.17
    psy
    -0.17
    èĴ¸
    -0.17
    POSITIVE LOGITS
    çļĦä¹łæĥ¯
    0.20
    æĺŃ
    0.20
    ä½łåľ¨
    0.19
    å¦ŀ
    0.18
    çĺ©
    0.18
    zac
    0.18
    .nano
    0.18
    abble
    0.18
    ç¾İè²Į
    0.18
     Css
    0.18
    Activations Density 0.003%

    No Known Activations