© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15191
    Prev
    Next
    INDEX
    Explanations

    help in or to

    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
    æľĢåIJĪéĢĤ
    -0.22
    ÑĪка
    -0.21
    åIJĪéĢĤ
    -0.19
    éĢĤåIJĪèĩªå·±
    -0.18
    建èŃ°
    -0.18
    ocator
    -0.18
     ná»Ńa
    -0.18
    çİ°çĬ¶
    -0.18
    é¦ĸè¦ģ
    -0.17
    ise
    -0.17
    POSITIVE LOGITS
    åľ¨äºİ
    0.23
     ÃŃch
    0.21
    fully
    0.21
    çIJĨ解åĴĮ
    0.21
    çĵ¢
    0.20
    ç¡®ç«ĭ
    0.20
    åľ¨çĶŁæ´»ä¸Ń
    0.20
    å·©åĽº
    0.19
    éģ¿åħį
    0.19
    à¹ĥà¸Ļà¸ģาร
    0.19
    Activations Density 0.055%

    No Known Activations