© 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. 10711
    Prev
    Next
    INDEX
    Explanations

    place names, city names

    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
    tick
    -0.21
    æĽ´éĩįè¦ģ
    -0.21
     tick
    -0.21
     fares
    -0.21
     et
    -0.20
     tap
    -0.19
    èĬĤ
    -0.19
    æĿ¥çľĭçľĭ
    -0.19
     lately
    -0.19
    红线
    -0.19
    POSITIVE LOGITS
    æĬĢæľ¯æľįåĬ¡
    0.23
    _suite
    0.19
    åĽŀåIJĪ
    0.19
    æĸijæĸĵ
    0.19
    -suite
    0.19
    colo
    0.19
    çĸĹç¨ĭ
    0.19
    å°±è¯Ĭ
    0.19
    angelo
    0.19
    å·¥ä½ľå²Ĺä½į
    0.19
    Activations Density 0.058%

    No Known Activations