© 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. 12749
    Prev
    Next
    INDEX
    Explanations

    graduation ceremonies

    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
    æĭľè®¿
    -0.19
    æ¶ĪåĮĸ
    -0.19
     afore
    -0.18
    .Named
    -0.18
    çģ¶
    -0.18
     woo
    -0.18
    åł¤
    -0.18
     stove
    -0.18
    çķĮçļĦ
    -0.17
    æ·«
    -0.17
    POSITIVE LOGITS
    /popper
    0.25
    åħ¸ç¤¼
    0.24
     вÑĭпÑĥÑģк
    0.23
    æĻºèĥ½åĪ¶éĢł
    0.22
     recess
    0.21
     graduation
    0.20
    _grad
    0.20
    åѦä½į
    0.20
     Spring
    0.19
     ceremonies
    0.19
    Activations Density 0.008%

    No Known Activations