© 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. 10636
    Prev
    Next
    INDEX
    Explanations

    are permitted / are met

    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
    çļ¿
    -0.23
    ç¬ı
    -0.20
    IBC
    -0.20
    uges
    -0.19
    .cloud
    -0.18
    ãģ°ãģĭãĤĬ
    -0.18
    åĦĨ
    -0.18
    èĽĬ
    -0.18
    è¾Ħ
    -0.18
    apos
    -0.17
    POSITIVE LOGITS
    羣æĺ¯
    0.20
    æıIJåIJį
    0.20
    reen
    0.19
    å¢ŀåĢ¼æľįåĬ¡
    0.19
     Gerçek
    0.18
    æ»Ķ
    0.18
     Assoc
    0.18
     react
    0.18
    ä½ľåĵģåĨħ容
    0.18
    éĹ®éĹ®
    0.18
    Activations Density 0.003%

    No Known Activations