© 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. 10650
    Prev
    Next
    INDEX
    Explanations

    Q: / introduction / meet

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ORMAT
    -0.21
    .utf
    -0.20
     Proud
    -0.18
    .Branch
    -0.18
    ynet
    -0.18
     Exxon
    -0.18
    éĥ¯
    -0.18
    .LENGTH
    -0.18
    åIJĮèĥŀ
    -0.18
    (HttpStatusCode
    -0.17
    POSITIVE LOGITS
    å¦Ĩ
    0.24
    åĮĸå¦Ĩ
    0.21
     ddl
    0.20
    æľīèī²
    0.20
    æĪĸå¤ļ
    0.20
     colours
    0.19
    类产åĵģ
    0.19
    ç´«èī²
    0.19
    å¼ĢçĽĺ
    0.18
    å¦Ŀ
    0.18
    Activations Density 0.012%

    No Known Activations