© 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. 17315
    Prev
    Next
    INDEX
    Explanations

    instructions or reminders

    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
    ·æĸ°
    -0.21
    ãģķãĤī
    -0.20
    æīĢ以ä»ĸ
    -0.19
    lettes
    -0.18
    é©·
    -0.17
    gee
    -0.17
    çİ©æĦı
    -0.17
    åīįåįģ
    -0.17
    огÑĢам
    -0.17
    bone
    -0.17
    POSITIVE LOGITS
    ance
    0.21
    è¦ģçŁ¥éģĵ
    0.19
    åĬ¡å¿ħ
    0.19
     rằng
    0.18
    åĭ¿
    0.18
     Oc
    0.18
    è¦ģ好好
    0.18
    ä¸Ģå®ļè¦ģ
    0.18
     liquids
    0.18
    ä¸įè¦ģ
    0.18
    Activations Density 0.011%

    No Known Activations