© 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. 13314
    Prev
    Next
    INDEX
    Explanations

    wiki, mx, MAC, MD

    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
    asted
    -0.23
    dek
    -0.23
    udas
    -0.20
    anan
    -0.20
    aises
    -0.19
    妥
    -0.19
    .destination
    -0.19
     Nigerian
    -0.19
    ourmet
    -0.19
    porto
    -0.19
    POSITIVE LOGITS
     sür
    0.20
     FIXME
    0.20
     ÐŁÐ¾Ñĩем
    0.20
     readable
    0.19
     variant
    0.19
    à¸Ľà¸²à¸ģ
    0.19
     mnemonic
    0.19
     teÅŁek
    0.19
     common
    0.19
    RefCount
    0.19
    Activations Density 0.291%

    No Known Activations