© 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. 13857
    Prev
    Next
    INDEX
    Explanations

    online commerce

    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
    scar
    -0.23
    ä¸ĢåľĪ
    -0.22
    ert
    -0.20
    uro
    -0.19
    ika
    -0.19
    ios
    -0.19
    ri
    -0.19
    li
    -0.19
    edian
    -0.19
    ine
    -0.18
    POSITIVE LOGITS
    åĵªå®¶å¥½
    0.23
    游æĪı代
    0.21
    chwitz
    0.21
    åĸĦäºİ
    0.21
    ãģĦãĤīãģ£
    0.20
    corlib
    0.20
    绸
    0.20
    andest
    0.20
    ityEngine
    0.19
    ãģĶè¦
    0.19
    Activations Density 0.018%

    No Known Activations