© 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. 12392
    Prev
    Next
    INDEX
    Explanations

    family names and lineage

    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£ħæī®
    -0.23
    Lead
    -0.20
    çģ¾åĮº
    -0.18
    Alternative
    -0.18
    æķĪçİĩ
    -0.18
    å¢ĥçķĮ
    -0.18
    人æĢ§åĮĸ
    -0.18
     envy
    -0.18
    sites
    -0.17
    yme
    -0.17
    POSITIVE LOGITS
    家æĹı
    0.44
    ä¸ī代
    0.42
    éģĹä¼ł
    0.38
    ä¼łæī¿
    0.37
     family
    0.36
    ä¸ĸ代
    0.36
    family
    0.35
    åIJİ代
    0.35
    åİĨåı²
    0.32
     generations
    0.31
    Activations Density 0.195%

    No Known Activations