© 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. 12365
    Prev
    Next
    INDEX
    Explanations

    well followed by Book

    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
    LOT
    -0.18
    udu
    -0.18
    aug
    -0.18
     roy
    -0.17
    CP
    -0.17
    å¾Īå¤ļäºĭæĥħ
    -0.17
     Republic
    -0.17
     happ
    -0.17
    дÑĢ
    -0.17
    æĽ´å¥½çļĦ
    -0.17
    POSITIVE LOGITS
     candidacy
    0.19
    ä¸Ńå¤ĸ
    0.19
    pty
    0.19
    é«ĺå±±
    0.19
    portun
    0.18
     Fraser
    0.18
     Emmanuel
    0.18
    çī¹åĪ«å£°æĺİ
    0.18
    轸
    0.17
    ptime
    0.17
    Activations Density 0.005%

    No Known Activations