© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11720
    Prev
    Next
    INDEX
    Explanations

    insurance plans, pricing, or benefits

    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
    æĸ°åħ´äº§ä¸ļ
    -0.22
     maj
    -0.21
    Hur
    -0.19
    ষ
    -0.18
    opot
    -0.18
    è¿Ļä¸ªåľ°åĽ¾
    -0.17
    lings
    -0.17
     Homo
    -0.16
    æ¤ħåŃIJ
    -0.16
    ä¹ĭä½ľ
    -0.16
    POSITIVE LOGITS
    agnostic
    0.23
    åı£å¾Ħ
    0.20
    å½¢å¼ı
    0.19
    è§Ħå®ļ
    0.19
    /groups
    0.18
    SEE
    0.18
    ungan
    0.18
    容éĩı
    0.17
    itre
    0.17
    åIJį称
    0.17
    Activations Density 0.006%

    No Known Activations