© 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. 16975
    Prev
    Next
    INDEX
    Explanations

    sharing and multiple users

    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
    迷失
    -0.20
    åıįçľģ
    -0.20
    ynn
    -0.20
    ÙģØŃ
    -0.19
    éĿ¢å¯¹éĿ¢
    -0.19
    åĽ´å¢Ļ
    -0.19
    糯米
    -0.18
    æĸ°åĵģ
    -0.18
    LError
    -0.18
     Russ
    -0.18
    POSITIVE LOGITS
    åħ±äº«
    0.49
     shared
    0.39
     Shared
    0.37
    åħ¬çĶ¨
    0.35
    Shared
    0.35
    èµĦæºIJåħ±äº«
    0.35
     Sharing
    0.34
     sharing
    0.33
    .shared
    0.32
    -shared
    0.32
    Activations Density 0.259%

    No Known Activations