© 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. 12750
    Prev
    Next
    INDEX
    Explanations

    centre or centers

    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
    ../../../
    -0.19
    uras
    -0.18
    ed
    -0.18
    /il
    -0.18
    edata
    -0.17
    erd
    -0.16
    edes
    -0.15
    lah
    -0.15
    liness
    -0.15
    boarding
    -0.15
    POSITIVE LOGITS
    coat
    0.17
    OfFile
    0.17
    pose
    0.16
    ise
    0.16
    iate
    0.16
    ises
    0.15
    ÙĬات
    0.15
    æĢĿæĥ³
    0.15
    ktor
    0.15
    ê°ĢëĬĶ
    0.15
    Activations Density 0.055%

    No Known Activations