© 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. 12446
    Prev
    Next
    INDEX
    Explanations

    utf-8 encoding and charset

    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
    ParallelGroup
    -0.23
    _Pods
    -0.20
    apg
    -0.20
    åı£æ°Ķ
    -0.20
    /controllers
    -0.19
    athom
    -0.19
    ipop
    -0.19
    _Parms
    -0.19
    :variables
    -0.19
    allas
    -0.19
    POSITIVE LOGITS
     Unicode
    0.28
     UTF
    0.27
    _unicode
    0.26
    .Unicode
    0.26
    .UTF
    0.25
    Unicode
    0.24
    æĸĩåŃĹ
    0.24
     encoding
    0.24
     compatibility
    0.23
     charset
    0.23
    Activations Density 0.209%

    No Known Activations