© 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. 13191
    Prev
    Next
    INDEX
    Explanations

    is/are followed by descriptions

    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
    _SUITE
    -0.22
    æĬĬè¿ĻäºĽ
    -0.19
    éħIJ
    -0.19
    äm
    -0.18
    ç¡®
    -0.18
    æģ°
    -0.18
    ç½ijç«Ļé¦ĸ页
    -0.17
    fte
    -0.17
    imos
    -0.17
    è´§
    -0.17
    POSITIVE LOGITS
     Capture
    0.19
    rut
    0.19
    ForRow
    0.18
    [now
    0.18
    ç»ıæµİ社ä¼ļ
    0.18
    éĻ·éĺ±
    0.18
    èµī
    0.17
     Speaker
    0.17
    é©Ń
    0.17
     Mint
    0.17
    Activations Density 0.023%

    No Known Activations