© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    parenting figures and relationships

    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
    举åįĹ
    -0.21
    éĵ¿
    -0.20
    IRM
    -0.20
    说çļĦæĺ¯
    -0.19
    å±±åºĦ
    -0.19
    èĥľä»»
    -0.19
    æľīæ¯Ĵ
    -0.19
    纪
    -0.19
    çİ°éĩij
    -0.19
    è¿Ļ家ä¼Ļ
    -0.18
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.27
    æĪijèĩªå·±
    0.23
     myself
    0.23
    èĩªå·±
    0.22
    对èĩªå·±
    0.21
    chod
    0.21
    åīįè¾Ī
    0.20
    DONE
    0.20
    åĪ«äºº
    0.19
    对æĪij
    0.19
    Activations Density 0.102%

    No Known Activations