© 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. 12811
    Prev
    Next
    INDEX
    Explanations

    budget, costs, funding, expenses

    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
    亿ä¸ĩ
    -0.28
    ä¸ĩ亿
    -0.23
     billions
    -0.22
    é¦ĸå¯Į
    -0.22
    -billion
    -0.20
     trillion
    -0.20
    illions
    -0.20
    essler
    -0.20
    ç§ģèIJ¥
    -0.20
    çĤ«èĢĢ
    -0.20
    POSITIVE LOGITS
    æ¯ıæľĪ
    0.26
    è¿IJ转
    0.25
     monthly
    0.23
    åľºåľ°
    0.23
    æ¯ıä½į
    0.22
    管çIJĨåĴĮ
    0.21
     MONTH
    0.21
    æ¯ı天
    0.21
    ç»´æĮģ
    0.21
    avar
    0.20
    Activations Density 0.027%

    No Known Activations