© 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. 12156
    Prev
    Next
    INDEX
    Explanations

    glossy, shiny, smooth finishes

    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
    æĢĢæĬ±
    -0.21
    è¾Ľè¾£
    -0.20
    ngen
    -0.20
     Crush
    -0.19
    éĥĩ
    -0.19
     Ragnar
    -0.19
    æ°ı
    -0.18
     Barnett
    -0.18
    utar
    -0.18
    æĢĢéĩĮ
    -0.18
    POSITIVE LOGITS
    åħīæ»ij
    0.31
     shiny
    0.28
     smooth
    0.27
     slick
    0.27
    åħīæ³½
    0.26
    滢
    0.26
    smooth
    0.24
     polished
    0.23
    èĢĢçľ¼
    0.23
     surfaces
    0.22
    Activations Density 0.032%

    No Known Activations