© 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. 10542
    Prev
    Next
    INDEX
    Explanations

    ah, Ah, Dah, Cah, Zah names

    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
    ively
    -0.18
    å±±åİ¿
    -0.18
    ities
    -0.17
    à¸Ĺาà¸ĩ
    -0.17
    ions
    -0.16
    дей
    -0.16
    ti
    -0.16
    Ļ
    -0.16
     minded
    -0.16
    uous
    -0.15
    POSITIVE LOGITS
    æĸ¥
    0.18
    rink
    0.17
    ccount
    0.17
    edral
    0.17
    åĴª
    0.17
    imizer
    0.16
    rist
    0.16
    sville
    0.16
    istorical
    0.16
    oor
    0.15
    Activations Density 0.146%

    No Known Activations