© 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. 13920
    Prev
    Next
    INDEX
    Explanations

    International Business Q

    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
    åIJį为
    -0.23
    ä¸ĬçļĦ
    -0.21
    setProperty
    -0.19
    ä¾Ľç»Ļ
    -0.18
    æĤį
    -0.18
    prite
    -0.18
    åľ¨äº¬
    -0.18
    æ±Ģ
    -0.18
    ìĥģ
    -0.18
    èIJ½æĪ·
    -0.17
    POSITIVE LOGITS
    å¥ĭæĪĺ
    0.19
    ä¸Ģéģį
    0.19
     Wolff
    0.19
    scala
    0.18
    arking
    0.18
    cy
    0.18
    çĶŁåij½
    0.18
    ä¹ĭæĪĺ
    0.18
    人æķ°
    0.17
    -hooks
    0.17
    Activations Density 0.005%

    No Known Activations