© 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. 10622
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb/state

    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
    让å®ĥ
    -0.21
    æĬĬå®ĥ
    -0.20
    æĿ¥è¿ĻéĩĮ
    -0.19
    éĥ½è®¤ä¸º
    -0.18
    è¿ĻäºĽéĹ®é¢ĺ
    -0.18
     McDon
    -0.18
    ç¿ķ
    -0.18
    è¿Ļåı¥è¯Ŀ
    -0.17
    åľ°è¯´
    -0.17
    åľ¨å¤ĸéĿ¢
    -0.17
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.19
    次
    0.19
    åıĬ缸åħ³
    0.19
    訴
    0.19
    /her
    0.18
    以åıĬåħ¶ä»ĸ
    0.18
    åĮ¿
    0.18
    çµ
    0.18
    gem
    0.18
    индивид
    0.17
    Activations Density 0.345%

    No Known Activations