© 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. 16294
    Prev
    Next
    INDEX
    Explanations

    research and scientific experiments

    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
    å²Ķ
    -0.20
    raham
    -0.20
    渲
    -0.20
    emens
    -0.19
    izza
    -0.19
    ä¸į妨
    -0.18
    -tier
    -0.18
     arsch
    -0.18
    bron
    -0.18
    Structured
    -0.18
    POSITIVE LOGITS
    å®ŀéªĮ
    0.30
    çłĶ究
    0.28
    éĩĩéĽĨ
    0.28
    ç§ijçłĶ
    0.27
    æĶ¶éĽĨ
    0.26
     experiment
    0.23
    缮çļĦ
    0.23
    ä¸ºçĽ®çļĦ
    0.23
    ç§ijåѦçłĶ究
    0.23
     experiments
    0.21
    Activations Density 0.023%

    No Known Activations