© 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. 17166
    Prev
    Next
    INDEX
    Explanations

    Masonry and mason

    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
    ustin
    -0.17
    asm
    -0.17
    kek
    -0.16
     Sanford
    -0.16
     sheer
    -0.16
    oding
    -0.16
    ìĸ¼
    -0.16
    usting
    -0.16
    éĻIJ度
    -0.15
    еÑĩение
    -0.15
    POSITIVE LOGITS
    ry
    0.21
    ifications
    0.17
    æĢ»å±Ģ
    0.17
    çĪ·
    0.16
    ennon
    0.16
    pole
    0.16
    mant
    0.16
    like
    0.16
    ically
    0.16
    boro
    0.16
    Activations Density 0.003%

    No Known Activations