© 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. 11393
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    backward
    -0.20
    Ëī
    -0.20
    Compound
    -0.19
    Ìģ
    -0.19
     moden
    -0.18
    为æĤ¨æıIJä¾Ľ
    -0.18
    åĸĭ
    -0.18
    éŨåīį
    -0.18
    compound
    -0.18
     Ashe
    -0.17
    POSITIVE LOGITS
    åĽ½éĻħåľ¨çº¿
    0.19
    поÑĤ
    0.18
    ernet
    0.18
    ety
    0.18
    PTS
    0.18
    enze
    0.18
    罡
    0.18
    è¿Ļä¹Łæĺ¯
    0.17
    sons
    0.17
     prelim
    0.17
    Activations Density 0.010%

    No Known Activations