© 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. 14224
    Prev
    Next
    INDEX
    Explanations

    so followed by adjective

    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
    äºĨä¸įå°ij
    -0.26
     bastante
    -0.23
    ä»Ģä¹Īåij¢
    -0.22
    å¾Ī大
    -0.21
    éĥ½æĺ¯éĿŀ常
    -0.21
    æĽ´å¤ļ
    -0.21
    å¾Īéĩįè¦ģ
    -0.21
     dần
    -0.20
    缸å½ĵ
    -0.20
    æĺ¯éĿŀ常
    -0.20
    POSITIVE LOGITS
    è¿ĻèĪ¬
    0.28
    å¦ĤæѤ
    0.28
    è¿Ļä¹Īå¤ļ
    0.24
    ä¾Ŀèµĸ
    0.20
    elpers
    0.20
    è¿Ļä¹Īä¹ħ
    0.20
    è¿Ļä¹Ī
    0.19
    itori
    0.19
     firepower
    0.18
    tte
    0.18
    Activations Density 0.038%

    No Known Activations