© 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. 16100
    Prev
    Next
    INDEX
    Explanations

    clinic, polytechnic, conservancy, university

    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
    è·Łä¸įä¸Ĭ
    -0.20
    ä¹ĸ
    -0.18
    oub
    -0.18
    们çļĦ
    -0.18
     pred
    -0.18
    è´º
    -0.17
    大家éĥ½åľ¨
    -0.17
     nied
    -0.17
     captivity
    -0.17
     captive
    -0.17
    POSITIVE LOGITS
    æĮ¤
    0.19
    ÑģÑĤво
    0.19
    forces
    0.19
    ment
    0.18
    ureau
    0.18
    åĬĽ
    0.18
    geb
    0.17
    amber
    0.17
    èħ±
    0.17
    åŃ
    0.17
    Activations Density 0.106%

    No Known Activations