© 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. 10583
    Prev
    Next
    INDEX
    Explanations

    legal names and titles

    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
    Negative Logits
     himself
    -0.26
     Ñģамого
    -0.23
    客
    -0.20
    åĴĮæĬĢæľ¯
    -0.20
    ahi
    -0.20
    ä¸Ģ身
    -0.19
    å¸ħæ°Ķ
    -0.19
     pun
    -0.19
    addy
    -0.19
    Howard
    -0.19
    POSITIVE LOGITS
    å¨ĺ家
    0.26
    å§IJ妹
    0.24
    -google
    0.21
    è£ĻåŃIJ
    0.21
    ä¸Ī夫
    0.21
    çĿ«
    0.20
    notation
    0.20
    å«ģç»Ļ
    0.20
    -Q
    0.19
    éĽĢ
    0.19
    Activations Density 0.167%

    No Known Activations