© 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. 16116
    Prev
    Next
    INDEX
    Explanations

    executive summary or overview

    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
    PX
    -0.20
    èģĶç³»æĪij们
    -0.20
    æ»ĺ
    -0.19
    دÙĪ
    -0.19
     Wish
    -0.18
    amu
    -0.18
    ITHER
    -0.18
    tro
    -0.18
    .ball
    -0.18
    讽
    -0.18
    POSITIVE LOGITS
    æ¦Ĥæĭ¬
    0.30
    æĮĪ
    0.28
     headline
    0.27
     summary
    0.26
    æıIJçĤ¼
    0.25
    è¦ģçĤ¹
    0.24
    æijĺè¦ģ
    0.23
     Summary
    0.23
    headline
    0.23
    -summary
    0.23
    Activations Density 0.109%

    No Known Activations