© 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. 10607
    Prev
    Next
    INDEX
    Explanations

    team or club actions

    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
    /request
    -0.20
    ä¸İä¼Ĺä¸įåIJĮ
    -0.20
    ä¸Ģ个人
    -0.19
    /basic
    -0.18
    å¦Ĥå®ŀ
    -0.18
    heimer
    -0.18
    çıŃéķ¿
    -0.18
    æĶ¶çº³
    -0.17
    expiration
    -0.17
    两个人
    -0.17
    POSITIVE LOGITS
    åĬ¡
    0.20
    æķ´ä½ĵ
    0.20
    çļĦæķ´ä½ĵ
    0.19
    éĩįå¿ĥ
    0.19
    iska
    0.19
    åħĪåīį
    0.18
    åīįä¸Ģ天
    0.18
    主è¦ģé¢Ĩ导
    0.18
    __.__
    0.18
    æĽ©
    0.18
    Activations Density 0.030%

    No Known Activations