© 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. 16773
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions

    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
    æŁı
    -0.20
    毫
    -0.19
    ä¸Ģç«Ļ
    -0.19
    stit
    -0.19
     Barker
    -0.18
    abyrinth
    -0.18
    .Require
    -0.18
    å¡«è¡¥
    -0.18
    èĢ½
    -0.18
    æĹ©æľŁ
    -0.18
    POSITIVE LOGITS
    身é«ĺ
    0.25
    äºĮ线
    0.22
    æĪIJ年人
    0.21
    ãĤµãĤ¤ãĤº
    0.20
    快讯
    0.20
    trs
    0.20
    妩
    0.20
    ç¾İå¦Ĩ
    0.19
     height
    0.19
    éĵ®
    0.19
    Activations Density 0.009%

    No Known Activations