© 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. 12062
    Prev
    Next
    INDEX
    Explanations

    mergers, acquisitions, and deals

    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¡Ļ
    -0.20
    иÑĦ
    -0.20
    thread
    -0.20
    æĹłç©·
    -0.20
    æĬ¥ä¸ļ
    -0.19
    éĹº
    -0.18
    女çĶŁ
    -0.18
     Ñĥзн
    -0.18
    æĺ¥è¿IJ
    -0.18
    责任å¿ĥ
    -0.18
    POSITIVE LOGITS
     merg
    0.26
    樽
    0.23
    并è´Ń
    0.22
    .Transfer
    0.20
    缸çĪ±
    0.20
     ruth
    0.19
    转移
    0.19
    æ´½
    0.19
    èijµ
    0.19
    óm
    0.19
    Activations Density 0.018%

    No Known Activations