© 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. 12768
    Prev
    Next
    INDEX
    Explanations

    awarded ranked named invited place

    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
     eventual
    -0.22
    æĿµ
    -0.20
    à¹Ģà¸Ĺศà¸ģา
    -0.20
    olf
    -0.20
    zt
    -0.19
    ç¼Ł
    -0.19
     eventually
    -0.19
    æĽ¾ç¶ĵ
    -0.18
     rue
    -0.18
     tv
    -0.18
    POSITIVE LOGITS
    æĸ°ãģŁ
    0.21
    两项
    0.20
     Nasıl
    0.20
    åıĪä¸Ģ次
    0.20
     Outcome
    0.19
    æıŃæĻĵ
    0.19
    ç¨Ģ
    0.19
    wig
    0.19
     science
    0.19
    åĨį次
    0.19
    Activations Density 0.057%

    No Known Activations