© 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. 11508
    Prev
    Next
    INDEX
    Explanations

    sudden stop or flash

    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
    çĨ¨
    -0.24
    å¥Ķæ³¢
    -0.23
    åĶł
    -0.22
    éĶ±
    -0.22
    æĬĺèħ¾
    -0.21
    éĢĽ
    -0.21
    çĨ¬
    -0.21
    æĹ¥æ¸IJ
    -0.21
    ucher
    -0.21
    çĨ¬å¤ľ
    -0.21
    POSITIVE LOGITS
    éĤ£ä¸ĢåĪ»
    0.31
    æĹ¶æľº
    0.27
    çŀ¬éĹ´
    0.27
    åĪ¹éĤ£
    0.27
    ä¸Ģçŀ¬éĹ´
    0.26
    çªģçĦ¶
    0.25
    çĮĽçĦ¶
    0.24
    ãĤ¿ãĤ¤ãĥŁãĥ³ãĤ°
    0.23
     ÑģобÑģÑĤвенно
    0.23
     sudden
    0.23
    Activations Density 0.056%

    No Known Activations