© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15400
    Prev
    Next
    INDEX
    Explanations

    web server container

    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
    趣
    -0.23
    è¯Ļ
    -0.22
    èĵij
    -0.22
    éĵ¡
    -0.20
    çŃ®
    -0.20
    å¾Ĺèµ·
    -0.19
    转æį¢
    -0.19
    ä¿®
    -0.19
    åĪĨæµģ
    -0.19
    èļ¤
    -0.18
    POSITIVE LOGITS
     диÑĢекÑĤоÑĢ
    0.19
    runtime
    0.19
    yü
    0.18
    _reserve
    0.18
    Ŀå§ĭ
    0.18
    ratings
    0.18
    é¹Į
    0.18
    аÑĢам
    0.18
    /Foundation
    0.18
    -bootstrap
    0.17
    Activations Density 0.035%

    No Known Activations