© 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. 11096
    Prev
    Next
    INDEX
    Explanations

    biography and work

    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
    çĮĹ
    -0.23
    æīĵæī°
    -0.23
    太快
    -0.23
    å¤įåıij
    -0.22
    为客æĪ·
    -0.22
    æ°´æ³µ
    -0.21
    æķıæį·
    -0.20
    å¿Ļç¢Į
    -0.20
    è¿ŀäºij
    -0.19
    软件
    -0.19
    POSITIVE LOGITS
     racial
    0.27
     interracial
    0.27
     NOI
    0.26
    -white
    0.23
     racist
    0.23
     Black
    0.22
     racially
    0.22
     whites
    0.22
    æ±īæĹı
    0.22
    ç§įæĹı
    0.21
    Activations Density 0.092%

    No Known Activations