© 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. 10977
    Prev
    Next
    INDEX
    Explanations

    legal names

    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
    媵
    -0.20
    åѤç«ĭ
    -0.19
    æ®ĩ
    -0.19
    é£İåIJ¹
    -0.19
    æ³Ľ
    -0.18
    èĹ©
    -0.18
    İ·
    -0.18
    亥
    -0.18
    æªĦ
    -0.18
    çĪ¨
    -0.18
    POSITIVE LOGITS
    IVA
    0.21
    åħ±äº§
    0.19
    .idea
    0.18
    æľīèĩªå·±çļĦ
    0.18
    omo
    0.18
    è´¢
    0.18
    czy
    0.18
    INGS
    0.18
     Bos
    0.17
     Drum
    0.17
    Activations Density 0.004%

    No Known Activations