© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    pairings, drabbles, characters, George Boateng

    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
    çļĦåĵģçīĮ
    -0.23
    éħįå¥Ĺ
    -0.20
    è¿Ļ个游æĪı
    -0.20
    çļĦèĢģ
    -0.20
    çļĦç¼ĺ
    -0.20
     squat
    -0.19
    çŁį
    -0.19
    æīįåıijçİ°
    -0.19
    è¿Ļå¥Ĺ
    -0.18
    PACKAGE
    -0.18
    POSITIVE LOGITS
    åı°è¯į
    0.21
    çłĶ讨
    0.20
    cie
    0.20
     males
    0.19
     male
    0.19
    æ·ĭ
    0.19
    人çī©
    0.19
    .serialize
    0.19
    ajan
    0.19
    主线
    0.18
    Activations Density 0.013%

    No Known Activations