© 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. 16129
    Prev
    Next
    INDEX
    Explanations

    rights reserved

    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
    çķª
    -0.23
    WER
    -0.18
    isce
    -0.18
    aland
    -0.18
    åģľ
    -0.18
    ronics
    -0.18
     Sans
    -0.18
    ovsky
    -0.17
    æľ¬èº«çļĦ
    -0.17
    åIJİéĿ¢çļĦ
    -0.17
    POSITIVE LOGITS
    æ°ijå¿ĥ
    0.19
    èµĦæºIJåħ±äº«
    0.19
    羸
    0.19
     od
    0.19
    èĽŁ
    0.18
    tech
    0.18
     Ashe
    0.18
    èijŃ
    0.18
    ä¸į对
    0.18
     usu
    0.18
    Activations Density 0.005%

    No Known Activations