© 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. 12063
    Prev
    Next
    INDEX
    Explanations

    stock tickers

    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
    Dragon
    -0.20
    æĪIJ为ä¸Ģ个
    -0.19
     Bas
    -0.18
     pog
    -0.18
     Squadron
    -0.18
     bas
    -0.18
    dragon
    -0.18
    踩
    -0.17
    am
    -0.17
    ----------
    -0.17
    POSITIVE LOGITS
    гаÑĢ
    0.20
    ktör
    0.20
    æł·åŃIJ
    0.20
    åĩ¿
    0.19
    éĶĪ
    0.19
    ãĤ·ãĥ§ãĥ¼
    0.19
     aracı
    0.19
    æĺİæĻ°
    0.19
    ä¸Ŀä¸Ŀ
    0.19
    ä¸Ģç»Ħ
    0.19
    Activations Density 0.047%

    No Known Activations