© 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. 14756
    Prev
    Next
    INDEX
    Explanations

    late or delayed timing

    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
    æĹ©æĹ¥
    -0.22
     sỼm
    -0.20
    anker
    -0.20
    çµ®
    -0.20
    çĸ±
    -0.19
    çĶŁäº§èĥ½åĬĽ
    -0.19
    sten
    -0.19
    ç²¹
    -0.19
    å°±åľ¨äºİ
    -0.19
     Termin
    -0.18
    POSITIVE LOGITS
    æīįä¼ļ
    0.25
    å§Ĺ
    0.24
    Delay
    0.22
    delay
    0.22
     delayed
    0.22
    _abstract
    0.20
    å»¶è¿Ł
    0.20
     delaying
    0.20
    Delayed
    0.20
    æīį
    0.20
    Activations Density 0.152%

    No Known Activations