© 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. 10347
    Prev
    Next
    INDEX
    Explanations

    distribution and splitting

    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
    ogy
    -0.21
    æĻ¦
    -0.20
    gend
    -0.20
     powder
    -0.20
    ellas
    -0.20
    jar
    -0.19
    ç²īæľ«
    -0.18
    cket
    -0.18
    assic
    -0.18
    å¾Ĺèµ·
    -0.18
    POSITIVE LOGITS
    åĪĨæµģ
    0.34
    æ±ĩéĽĨ
    0.26
    æ±ĩèģļ
    0.25
    æŀ¢çº½
    0.25
    åĪĨè£Ĥ
    0.25
    åĪĨãģij
    0.21
    æ±ĩæĢ»
    0.21
     distributing
    0.21
    ä¸īæĿ¡
    0.21
     splitting
    0.20
    Activations Density 0.205%

    No Known Activations