© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12555
    Prev
    Next
    INDEX
    Explanations

    news headlines and announcements

    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
    éĺ¿æ£®
    -0.20
    åĪ»èĭ¦
    -0.20
     adr
    -0.20
    å·¾
    -0.19
    åįģ足
    -0.19
    æĻ®
    -0.18
    ä¸įæĸŃå¢ŀ强
    -0.18
    çĺ¿
    -0.18
    ulle
    -0.18
    ä¸Ĭå²Ĺ
    -0.17
    POSITIVE LOGITS
    æİī
    0.40
    æİīäºĨ
    0.35
    太快
    0.26
    åİŁåĽłæĺ¯
    0.26
    åİŁåĽł
    0.25
    æįŁå¤±
    0.24
    主è¦ģåİŁåĽł
    0.23
    (loss
    0.23
     Reasons
    0.22
    èĥ¶åĽĬ
    0.22
    Activations Density 0.156%

    No Known Activations