© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 15740
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols after separators

    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
    ase
    -0.21
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.21
    asing
    -0.19
     cand
    -0.19
    ä»İä¸ļ
    -0.19
    æ¹
    -0.18
    <<
    -0.18
    ymb
    -0.18
    ieder
    -0.18
    çIJĨè§£åĴĮ
    -0.18
    POSITIVE LOGITS
    è·º
    0.21
    åĪĨåĪ«ä¸º
    0.21
    æľĢåıĹæ¬¢è¿İ
    0.19
    åĪ«çļĦ
    0.19
    æ°¸ä¸į
    0.19
    åİ¥
    0.18
    aroo
    0.18
    æıĸ
    0.18
    æĬķè¯ī
    0.18
    ä½łèĩªå·±
    0.17
    Activations Density 0.112%

    No Known Activations