© 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. 10455
    Prev
    Next
    INDEX
    Explanations

    protests, chanting, slogans

    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
    è¿Ļå¥Ĺ
    -0.20
    éħĮ
    -0.20
    åħ¨å¥Ĺ
    -0.19
    缴éĢļ车
    -0.19
    ç»Ĵ
    -0.19
     Colomb
    -0.18
     Subscribe
    -0.18
    ä¸Ģç¬ij
    -0.18
    urret
    -0.18
    LOSS
    -0.17
    POSITIVE LOGITS
    ä¸Ģéģį
    0.20
    èµĦæľ¬å¸Ĥåľº
    0.20
    çĸ¾
    0.19
     altern
    0.18
     "
    0.18
     '
    0.18
    yll
    0.18
     collective
    0.18
     bio
    0.18
     leader
    0.18
    Activations Density 0.004%

    No Known Activations