© 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. 14306
    Prev
    Next
    INDEX
    Explanations

    drops, pair, or micro quantities

    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
    ä¸Ģç¬Ķ
    -0.24
    åħ±åIJĮä½ĵ
    -0.23
    è¿ĻåĿĹ
    -0.20
     ØŃÙĤ
    -0.20
    ä¸ĢåĿĹ
    -0.20
    åħ¸
    -0.19
    ål
    -0.18
    æ¼ĵ
    -0.18
    åIJĦ个çݯèĬĤ
    -0.18
    ustin
    -0.18
    POSITIVE LOGITS
    客æĪ·æľįåĬ¡
    0.20
    /ns
    0.19
    èĤĭ
    0.19
     Quadr
    0.18
    /cards
    0.18
    代价
    0.18
     cloak
    0.17
    âĬĬ
    0.17
    åĽ½åĢº
    0.17
    çħ¨
    0.17
    Activations Density 0.007%

    No Known Activations