© 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. 13545
    Prev
    Next
    INDEX
    Explanations

    clerk's office

    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
    Ń
    -0.20
    åĪ«çļĦ
    -0.19
     Chow
    -0.18
    arsity
    -0.18
    LECT
    -0.18
    èĢħãģĮ
    -0.18
    èĥĮæĻ¯ä¸ĭ
    -0.18
    ridor
    -0.17
    æĴ¼
    -0.17
    éĨħ
    -0.17
    POSITIVE LOGITS
    æĪ¿
    0.22
    å©ļ姻
    0.22
    å¤ĸåĮħ
    0.20
    ldata
    0.20
     clerk
    0.19
    enumer
    0.19
    æĹ¥å¸¸å·¥ä½ľ
    0.19
    ä¿Ŀ管
    0.18
     Truth
    0.18
    羣çIJĨ
    0.17
    Activations Density 0.012%

    No Known Activations