© 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. 10488
    Prev
    Next
    INDEX
    Explanations

    playoffs

    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
    è¿ľå¤Ħ
    -0.23
    èĢģ人家
    -0.22
    éĤij
    -0.20
    .grad
    -0.20
    纸ä¸Ĭ
    -0.20
    两人
    -0.19
    æĸĭ
    -0.19
    读åIJİ
    -0.19
    olls
    -0.19
    åħ©äºº
    -0.18
    POSITIVE LOGITS
    lsa
    0.27
    ör
    0.21
    赫
    0.19
    adjusted
    0.18
    cola
    0.18
    ä¼ĺäºİ
    0.18
    çħ§æł·
    0.17
     Gir
    0.17
     Uint
    0.17
    .bootstrap
    0.17
    Activations Density 0.025%

    No Known Activations