© 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. 16368
    Prev
    Next
    INDEX
    Explanations

    planning for trips and events

    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
    berger
    -0.19
    eced
    -0.18
    èĭ±æīį
    -0.18
    è´«ç©·
    -0.18
    å¹²ä»Ģä¹Ī
    -0.18
    inem
    -0.18
    elf
    -0.18
    .setParameter
    -0.17
    è´«åĽ°
    -0.17
    å¾Īæ¸ħæ¥ļ
    -0.17
    POSITIVE LOGITS
    å¿ħå¤ĩ
    0.22
    ä¸ŃçļĦ
    0.22
     or
    0.22
    é¦ĸéĢī
    0.21
    åĴĮ个人
    0.21
    头æĿ¡
    0.20
    å¢ŀæ·»
    0.20
    离ä¸įå¼Ģ
    0.20
    æĪĸå°Ĩ
    0.19
    ä¸ŃæľĢ
    0.19
    Activations Density 0.112%

    No Known Activations