© 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. 12002
    Prev
    Next
    INDEX
    Explanations

    event descriptors

    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
    稳
    -0.21
    amation
    -0.20
    æĸ°çļĦä¸Ģ
    -0.18
    éķĽ
    -0.18
    ByEmail
    -0.18
    ä¸ĢéĹª
    -0.17
    é¾Ľ
    -0.17
    å¾Īæĺ¯
    -0.17
     tslint
    -0.17
    亲çĪ±
    -0.17
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.19
    ież
    0.19
    侥幸
    0.18
     ÑĤоже
    0.18
    ä¹Łåľ¨
    0.18
    ä¹Łæ²¡
    0.18
    åĪĻæĺ¯
    0.17
     miejs
    0.17
    粤港澳
    0.17
    åīįèĢħ
    0.17
    Activations Density 2.033%

    No Known Activations