© 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. 10796
    Prev
    Next
    INDEX
    Explanations

    finish, shine, or coating

    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
    å´İ
    -0.22
    广
    -0.21
    éħ
    -0.20
    éĻį温
    -0.19
    æĶ¹éĢł
    -0.19
     giấc
    -0.19
    çĶŁçī©åѦ
    -0.18
    жение
    -0.18
    飧
    -0.18
    -margin
    -0.18
    POSITIVE LOGITS
    ä¿Ŀåħ»
    0.26
     upkeep
    0.25
    ç»´æĬ¤
    0.23
    æľīèī²
    0.21
    å®ĺåħµ
    0.21
     plaque
    0.20
    é¢ľèī²
    0.20
     fingerprints
    0.20
    驳
    0.20
    çĸ¤
    0.20
    Activations Density 0.023%

    No Known Activations