© 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. 16965
    Prev
    Next
    INDEX
    Explanations

    fat, shortening, corn, plant, hydrogenation

    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
     ÄIJÄĥng
    -0.22
     Bare
    -0.21
    eve
    -0.20
    èµ°åĩºåİ»
    -0.20
    bare
    -0.18
    çĻ»è®°
    -0.18
    ä¸Ģæľ¬ä¹¦
    -0.18
     bare
    -0.18
    éĽĨæĪIJ
    -0.18
    æĸĩ书
    -0.18
    POSITIVE LOGITS
    rail
    0.26
     cashier
    0.20
    orts
    0.19
     dá»±ng
    0.18
    creation
    0.18
    lush
    0.18
    åİĤåķĨ
    0.17
    riminal
    0.17
    poons
    0.17
    éĢł
    0.17
    Activations Density 0.006%

    No Known Activations