© 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. 12594
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    æĸ°å¸¸æĢģ
    -0.26
     Tumblr
    -0.19
     tumblr
    -0.19
    æĢľ
    -0.18
    nga
    -0.18
    åĪĽå®¢
    -0.17
    们éĥ½
    -0.17
    cales
    -0.17
    åĴĶ
    -0.17
    aming
    -0.17
    POSITIVE LOGITS
    subst
    0.20
    Ùħت
    0.18
    UTION
    0.16
    åIJĮæĦı
    0.16
    ERSION
    0.16
    eler
    0.16
    é²į
    0.15
    ä¸Ģåī¯
    0.15
    ROTO
    0.15
    ãģ¾ãģĻ
    0.15
    Activations Density 0.098%

    No Known Activations