© 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. 17080
    Prev
    Next
    INDEX
    Explanations

    Kaiser, Halifax, Bayern, firebase

    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
    ¹
    -0.22
    ition
    -0.20
    most
    -0.19
    ting
    -0.19
    tl
    -0.17
    ness
    -0.17
    iness
    -0.16
    ç¬ijè¯Ŀ
    -0.16
    ter
    -0.16
    æĻŀ
    -0.16
    POSITIVE LOGITS
    ä¹İ
    0.23
    LY
    0.19
    loh
    0.19
    åĮĸçļĦ
    0.18
    alty
    0.17
    kir
    0.17
    otas
    0.17
    uos
    0.17
    éĢ¦
    0.17
     Redistribution
    0.16
    Activations Density 0.005%

    No Known Activations