© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17293
    Prev
    Next
    INDEX
    Explanations

    name, surname, color, etymology, panic

    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
    Negative Logits
    åħĢ
    -0.24
    游
    -0.19
     peter
    -0.19
    çĦ¦çĤ¹
    -0.19
    åĽ½åºĨ
    -0.18
    天åłĤ
    -0.18
    åĮĸçļĦ
    -0.18
    æĶ¯çº¿
    -0.18
    @author
    -0.18
    åĿĩ为
    -0.18
    POSITIVE LOGITS
     unm
    0.22
    bih
    0.21
    opcode
    0.20
    åİĨåı²æĸĩåĮĸ
    0.20
     carving
    0.19
    åİĨåı²ä¸Ĭ
    0.19
    祯
    0.19
    ä¸ĸçķĮåIJĦåľ°
    0.19
    ppv
    0.19
     carve
    0.19
    Activations Density 0.015%

    No Known Activations