© 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. 10676
    Prev
    Next
    INDEX
    Explanations

    loan application and credit assessment

    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
    顺
    -0.23
    ä¾ĥ
    -0.20
    éłĨ
    -0.19
    å¨ģèĥģ
    -0.19
    yro
    -0.19
    stringValue
    -0.19
    çĻĤ
    -0.19
    .jquery
    -0.19
     lá»±a
    -0.19
    ponder
    -0.18
    POSITIVE LOGITS
    ä¿¡è´·
    0.24
    å¿«æį·
    0.22
    çĦī
    0.20
    èĻĽ
    0.20
    åĢŁæ¬¾
    0.20
    é£İæݧ
    0.20
     credit
    0.19
    è¿Ľåĩºåı£
    0.19
    æĭħä¿Ŀ
    0.19
    çļĦåIJĦ项
    0.19
    Activations Density 0.012%

    No Known Activations