© 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. 12709
    Prev
    Next
    INDEX
    Explanations

    curtain or curt

    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
    èİł
    -0.17
    å¿ĥæĦ¿
    -0.17
    -0.17
    ¼
    -0.17
    es
    -0.16
    лÑİ
    -0.16
    acre
    -0.16
    erman
    -0.16
    åĻ¨åħ·
    -0.16
    ibernate
    -0.16
    POSITIVE LOGITS
    lining
    0.20
    doors
    0.17
    adol
    0.17
     sos
    0.16
    Ø®ÙĬ
    0.16
    eus
    0.16
    -door
    0.16
    lain
    0.16
    anca
    0.15
    ein
    0.15
    Activations Density 0.005%

    No Known Activations