© 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. 14909
    Prev
    Next
    INDEX
    Explanations

    curfew, arrest, timeout, measures

    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
    竺
    -0.19
    TERS
    -0.19
    éģĵ士
    -0.19
    misc
    -0.19
    éļ¶
    -0.18
    depart
    -0.18
    åĸ
    -0.17
    æľīæĽ´å¤ļçļĦ
    -0.17
    åĿĽ
    -0.17
    èī¯æĢ§
    -0.17
    POSITIVE LOGITS
    å±ĢéĿ¢
    0.23
    æľŁéĹ´
    0.23
    éĢļçŁ¥ä¹¦
    0.22
    令
    0.20
    æݪæĸ½
    0.20
    æľŁ
    0.20
    agra
    0.20
    åĪ¶åº¦
    0.20
    模å¼ı
    0.19
    ForObject
    0.19
    Activations Density 0.007%

    No Known Activations