© 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. 16232
    Prev
    Next
    INDEX
    Explanations

    transitioning or becoming

    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
    好ä¸į好
    -0.25
    æľĢæĸ°
    -0.23
    æĺ¨æĻļ
    -0.21
    缮åīįæŃ£åľ¨
    -0.20
    缮åīį为æŃ¢
    -0.20
    缮åīį
    -0.20
    åIJ¦åĪĻ
    -0.20
     otherwise
    -0.19
    å·²äºİ
    -0.18
    çķĮ第ä¸Ģ
    -0.18
    POSITIVE LOGITS
    éĢIJæ¸IJ
    0.39
    æ¸IJæ¸IJ
    0.35
     dần
    0.33
     gradually
    0.31
    æħ¢æħ¢
    0.31
     became
    0.30
    æĽ´ä¸º
    0.30
    éĢIJæŃ¥
    0.29
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.29
    æĽ´åĬł
    0.28
    Activations Density 0.198%

    No Known Activations