© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    Helsinki, Estonian, inn

    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
    æīĭæ³ķ
    -0.20
    عة
    -0.19
    imator
    -0.19
    驸
    -0.18
    èĪĤ
    -0.18
    æľ¯è¯Ń
    -0.18
    åķĸ
    -0.18
    ç½Ĥ
    -0.17
    illac
    -0.17
    inals
    -0.17
    POSITIVE LOGITS
    èIJ¥åķĨ
    0.21
    å¾¼
    0.20
    æijĨåľ¨
    0.19
    å³°ä¼ļ
    0.18
    æĥľ
    0.18
    zure
    0.17
    omer
    0.17
    èĩ
    0.17
    蹿
    0.17
    icher
    0.17
    Activations Density 0.002%

    No Known Activations