© 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. 17280
    Prev
    Next
    INDEX
    Explanations

    few things, way too, not many

    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
    åħ¥æĪ·
    -0.27
    TRANS
    -0.20
    äºĽä»Ģä¹Ī
    -0.20
    æľ¬èº«çļĦ
    -0.19
    æľ¬æĬ¥
    -0.18
    ÑĦа
    -0.18
    Ñĥз
    -0.18
    ä»Ģä¹Īéĥ½ä¸į
    -0.18
    æĬĺèħ¾
    -0.17
    OLD
    -0.17
    POSITIVE LOGITS
     anyone
    0.25
     someone
    0.24
    someone
    0.21
    ä¸Ģå¥Ĺ
    0.21
    åĵªä¸Ģ个
    0.21
     debate
    0.20
    åIJ¬è¿ĩ
    0.20
    ero
    0.20
     blanket
    0.20
    第äºĮ个
    0.19
    Activations Density 0.053%

    No Known Activations