© 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. 14730
    Prev
    Next
    INDEX
    Explanations

    decision Making

    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
    æĥ³æĥ³
    -0.19
     Ñģобой
    -0.19
    åįİ侨
    -0.18
    æĥ³è±¡åĬĽ
    -0.17
     uLocal
    -0.17
    çŀŃ解並
    -0.17
    æĦıè§ģ建议
    -0.17
     ÑģебÑı
    -0.17
    å¥¥åľ°
    -0.17
    æĥ³çŁ¥éģĵ
    -0.16
    POSITIVE LOGITS
    naire
    0.28
    nable
    0.20
    naires
    0.19
    èĢħ
    0.18
    nel
    0.18
    æĪIJè´¥
    0.17
    ãĥ£
    0.17
    ective
    0.17
    icity
    0.17
    åħ±åIJĮä½ĵ
    0.17
    Activations Density 0.028%

    No Known Activations