© 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. 15736
    Prev
    Next
    INDEX
    Explanations

    code or special characters

    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
    éķ¿å¾Ĺ
    -0.23
    fty
    -0.19
     Loc
    -0.19
    éªł
    -0.18
    heading
    -0.18
    era
    -0.18
    Gem
    -0.18
    éŀį
    -0.18
     Glob
    -0.18
    æľIJ
    -0.18
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.19
    çĤ¹åĩ»æŁ¥çľĭ
    0.19
    åĬŁ
    0.19
    ditor
    0.19
    æĿŃ
    0.19
    éģģ
    0.18
    ultan
    0.18
    zilla
    0.18
    ocoder
    0.18
    åŁº
    0.18
    Activations Density 0.240%

    No Known Activations