© 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. 15870
    Prev
    Next
    INDEX
    Explanations

    video game consoles and eras

    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
     giãn
    -0.21
     phoenix
    -0.19
    ONY
    -0.18
    qh
    -0.18
    ovsky
    -0.18
    gps
    -0.18
    edith
    -0.17
    åŁĤ
    -0.17
    髹
    -0.17
    è¿Ļä¹Īåģļ
    -0.17
    POSITIVE LOGITS
    æĹ¶æľŁ
    0.22
    æĹ¶æľŁçļĦ
    0.21
    -era
    0.20
    æ°´ä¸Ĭ
    0.20
    Exporter
    0.20
    åīįæľŁ
    0.19
    çĽĴ
    0.19
    大éĺª
    0.19
    è¿Ľé¡¹
    0.18
    AuthProvider
    0.18
    Activations Density 0.014%

    No Known Activations