© 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. 10603
    Prev
    Next
    INDEX
    Explanations

    Postgres, Day, Quarter, testing, variable 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
    Not in Any Lists

    No Comments

    Negative Logits
    Coach
    -0.20
    许
    -0.20
    æķĻç»ĥ
    -0.19
    anja
    -0.18
     coach
    -0.18
    åij¨äºĮ
    -0.18
     dif
    -0.18
    _STAR
    -0.18
    å·§
    -0.18
    coach
    -0.17
    POSITIVE LOGITS
    åIJį称
    0.37
    è¿Ļ个åIJįåŃĹ
    0.33
    åIJįåŃĹ
    0.32
    åij½åIJį
    0.31
     name
    0.29
    åIJį
    0.28
     tên
    0.27
    称åı·
    0.27
    åŃĹæł·
    0.26
    -name
    0.26
    Activations Density 0.893%

    No Known Activations