© 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. 10485
    Prev
    Next
    INDEX
    Explanations

    elements ending in ical or ism

    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
    å¹Į
    -0.20
    å§Ĭ妹
    -0.18
    æĶ¯æĮģ
    -0.18
    뼰
    -0.18
    æī¶æĮģ
    -0.18
    åĩºæĿ¥
    -0.18
     chợ
    -0.18
    æµļ
    -0.17
    SError
    -0.17
    Å¡e
    -0.17
    POSITIVE LOGITS
    龸çİĭ
    0.20
    ions
    0.20
    uele
    0.19
    æľĽçĿĢ
    0.19
    主é¢ĺæ´»åĬ¨
    0.19
    Pooling
    0.18
    åѦåĪ°
    0.18
    Sink
    0.18
    rts
    0.18
    çĶŁæ¶¯
    0.18
    Activations Density 0.001%

    No Known Activations