© 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. 14081
    Prev
    Next
    INDEX
    Explanations

    dates in months

    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
    æ£Ģ
    -0.18
    ued
    -0.18
    è¡¡
    -0.17
    åĪ¶æľį
    -0.17
    umi
    -0.17
     retrie
    -0.17
    毫ä¸į
    -0.17
     reprodu
    -0.17
    combo
    -0.17
    ä»Ģä¹Īåľ°æĸ¹
    -0.17
    POSITIVE LOGITS
    Å¡ÃŃ
    0.24
    两天
    0.20
    ä¸ī天
    0.19
    两åij¨
    0.19
    çªģ
    0.19
    ä»ĸèĩªå·±
    0.19
    åĿĬ
    0.18
    第äºĮ天
    0.18
    æĿijåŃIJ
    0.18
    tone
    0.17
    Activations Density 0.017%

    No Known Activations