© 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. 12765
    Prev
    Next
    INDEX
    Explanations

    and list items

    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
     denial
    -0.21
     WA
    -0.21
     Augusta
    -0.19
     gaz
    -0.19
    çĦ¦çĤ¹
    -0.19
     news
    -0.18
    umlah
    -0.18
    骡
    -0.18
    anium
    -0.18
    ç«ĸ
    -0.18
    POSITIVE LOGITS
    ä¿Ŀåħ»
    0.26
    æŃ£å¸¸ä½¿çĶ¨
    0.24
    使çĶ¨å¯¿åij½
    0.23
     иÑģполÑĮзованиÑı
    0.23
    Instructions
    0.23
    使çĶ¨
    0.22
    注æĦıäºĭ项
    0.22
     пÑĢоÑĩ
    0.21
     иÑģполÑĮзоваÑĤÑĮ
    0.21
     Instructions
    0.21
    Activations Density 0.016%

    No Known Activations