© 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. 14423
    Prev
    Next
    INDEX
    Explanations

    digit sequences

    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
    è¿ĺå°Ĩ
    -0.21
    ä¸İæѤåIJĮæŶ
    -0.19
    å°Ĩèĩªå·±çļĦ
    -0.18
    è¿ĺåı¯ä»¥
    -0.17
    (empty
    -0.17
    å°Ĩ
    -0.17
    ives
    -0.17
    .zh
    -0.17
    çĭ¬
    -0.17
     children
    -0.17
    POSITIVE LOGITS
    æīĴ
    0.21
    åıĤè°ĭ
    0.21
    çĦ¶
    0.19
    apolis
    0.19
    lope
    0.18
    entrant
    0.18
    æĵĺ
    0.18
    祧
    0.18
    å·¥ä½ľå²Ĺä½į
    0.18
    åħ»æĬ¤
    0.18
    Activations Density 0.165%

    No Known Activations