© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16716
    Prev
    Next
    INDEX
    Explanations

    names from fiction/literature

    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
     banc
    -0.21
     абÑģолÑİÑĤно
    -0.21
    路人
    -0.21
    åŃIJåŃĻ
    -0.21
     Gad
    -0.20
    ä¸įåĪ°
    -0.20
    åģİ
    -0.20
    ajs
    -0.19
    åij
    -0.19
    篷
    -0.19
    POSITIVE LOGITS
    å¼ķåħ¥
    0.21
    (optional
    0.19
    äºĭæķħåıijçĶŁ
    0.19
    æİ¥åħ¥
    0.19
    å¤ĸæı´
    0.18
     hosted
    0.18
     gợi
    0.18
    çļĦæķĻåѦ
    0.18
    æĭħ
    0.18
    ãĥijãĤ½
    0.18
    Activations Density 0.013%

    No Known Activations