© 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. 12783
    Prev
    Next
    INDEX
    Explanations

    composite materials containing fibers

    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
    ulg
    -0.20
     Bowen
    -0.20
    æľīèī²
    -0.19
    念
    -0.19
     Immediate
    -0.19
    æ¯ıä¸Ģ天
    -0.18
    getQuery
    -0.18
    ä¸Ńå±±
    -0.18
     Cree
    -0.18
     visit
    -0.18
    POSITIVE LOGITS
    åµĮ
    0.30
     embedded
    0.25
    çĤ¹ç¼Ģ
    0.25
    æ··
    0.24
     embed
    0.22
    bur
    0.21
    åIJ«ãģ¾ãĤĮ
    0.21
    åIJ«éĩı
    0.21
    content
    0.20
    åľ¨éĩĮéĿ¢
    0.20
    Activations Density 0.207%

    No Known Activations