© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12260
    Prev
    Next
    INDEX
    Explanations

    book titles or film titles

    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
    è¿ijäºĽ
    -0.20
    çĽ¾
    -0.20
    çĦ¶
    -0.20
    çĦ¶èĢĮ
    -0.20
    æĹ¥å¤ľ
    -0.20
    èħ¾é£ŀ
    -0.19
    åIJ¦
    -0.19
    è¾Ł
    -0.19
    æŁĶåĴĮ
    -0.19
    åºĩ
    -0.19
    POSITIVE LOGITS
    .rcParams
    0.21
    åĨĮ
    0.20
    _tm
    0.20
    олов
    0.20
     Kl
    0.19
    åīįåįģ
    0.19
    æĺ¯ä¸Ģ件
    0.19
    dot
    0.19
    第ä¸Ģç«ł
    0.18
    讲
    0.18
    Activations Density 0.100%

    No Known Activations