© 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. 13888
    Prev
    Next
    INDEX
    Explanations

    Vancouver

    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
    CellValue
    -0.19
    京津
    -0.17
    ãģĵãģ¨
    -0.16
    ãģ¾ãģ¾
    -0.16
    Êĭ
    -0.16
    emy
    -0.16
    enu
    -0.16
    鸷
    -0.16
    èĨº
    -0.16
    emap
    -0.16
    POSITIVE LOGITS
    èĬĻèĵī
    0.18
    ities
    0.18
    hire
    0.18
    erne
    0.18
    ستاÙĨ
    0.17
    stry
    0.17
    ä¸īäºļ
    0.17
    åį«è§Ĩ
    0.17
    èĶ½
    0.17
    rypt
    0.17
    Activations Density 0.014%

    No Known Activations