© 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. 10612
    Prev
    Next
    INDEX
    Explanations

    phone numbers and addresses

    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
    èī²
    -0.19
    å¯ŀ
    -0.18
    imson
    -0.18
    roe
    -0.17
    rise
    -0.17
    ä½İä»·
    -0.17
    å¥ł
    -0.17
     coloring
    -0.17
    æĭ¼
    -0.17
    å·´å·´
    -0.17
    POSITIVE LOGITS
     Telephone
    0.22
     PHONE
    0.20
    æīĭæľº
    0.20
     Fir
    0.19
    /F
    0.19
     ÑĤелеÑĦ
    0.19
    /IP
    0.19
     phone
    0.18
    åĽłä¸ºä½ł
    0.18
    -phone
    0.18
    Activations Density 0.007%

    No Known Activations