© 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. 12469
    Prev
    Next
    INDEX
    Explanations

    age

    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
    诡
    -0.21
     sırasında
    -0.21
    ikon
    -0.20
    å®ĮåĸĦ
    -0.20
    åı¦ä¸ĢåįĬ
    -0.20
    ä¸Ģ个å°ı
    -0.19
    åIJĦ个çݯèĬĤ
    -0.19
    å®Įåħ¨ä¸įåIJĮ
    -0.19
    ä¸Ģæłĭ
    -0.19
     Büyük
    -0.19
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.24
     age
    0.23
     whatsoever
    0.23
    å°Ĭ严
    0.20
    ÑĢог
    0.19
    bian
    0.19
    -age
    0.19
     any
    0.19
    (age
    0.19
     Age
    0.18
    Activations Density 0.021%

    No Known Activations