© 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. 15190
    Prev
    Next
    INDEX
    Explanations

    year earlier, year on year, year ago

    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
    cov
    -0.21
    iw
    -0.21
    oj
    -0.20
    ilian
    -0.19
    å·§
    -0.18
    //*
    -0.18
    个人è§ĤçĤ¹
    -0.18
     Solar
    -0.18
     Cov
    -0.18
    <!--
    -0.17
    POSITIVE LOGITS
    enic
    0.21
     اÙĦÙĪاØŃد
    0.21
    rvine
    0.20
    éĤ£è¾¹
    0.20
    豺
    0.19
    èĤ©
    0.19
    èį©
    0.19
    æĮģå¹³
    0.19
     ÑģиÑĤ
    0.18
    /global
    0.18
    Activations Density 0.048%

    No Known Activations