© 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. 10536
    Prev
    Next
    INDEX
    Explanations

    post this

    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
    /from
    -0.21
    sted
    -0.19
    åı¯èĥ½åĩºçİ°
    -0.19
    æ²Ķ
    -0.18
    .viewport
    -0.18
    иÑĤелÑĮно
    -0.18
     Vernon
    -0.18
     Ñģобой
    -0.17
    untas
    -0.17
    åļ¼
    -0.17
    POSITIVE LOGITS
    äºĽä»Ģä¹Ī
    0.25
    æѤæĸĩ
    0.25
    å°ijéĩı
    0.23
     something
    0.21
    缸åħ³åĨħ容
    0.21
    åħ³äºİ
    0.20
    äºĽ
    0.20
    è¶³å¤ŁçļĦ
    0.19
    æĪIJæŀľ
    0.19
    æľīåħ³
    0.19
    Activations Density 0.041%

    No Known Activations