© 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. 12097
    Prev
    Next
    INDEX
    Explanations

    award winner told

    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
    æĶ
    -0.20
    aru
    -0.19
    -dev
    -0.18
    ImageContext
    -0.18
    uell
    -0.17
    缸è¿ij
    -0.17
    èŁ
    -0.17
    å¼ĢåıijåĮº
    -0.17
    笼
    -0.17
    éĥ¨åī¯
    -0.17
    POSITIVE LOGITS
    è¿ĺ羣
    0.18
    è¯Ĩ
    0.18
    累计
    0.18
     lov
    0.18
    罡
    0.18
     McMaster
    0.18
    ä¸į妨
    0.18
    çłģ
    0.18
    fol
    0.18
    æ´ĹèĦ¸
    0.17
    Activations Density 0.307%

    No Known Activations