© 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. 11923
    Prev
    Next
    INDEX
    Explanations

    previously considered or perceived

    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
    缮åīįæŃ£åľ¨
    -0.30
    缮åīį
    -0.27
     presently
    -0.26
    缮åīį为æŃ¢
    -0.25
    currently
    -0.25
     currently
    -0.24
    å±ĬæŶ
    -0.24
    æľ¬æľŁ
    -0.24
    ä¹Łå¥½
    -0.23
    缮åīįåĽ½åĨħ
    -0.23
    POSITIVE LOGITS
     simply
    0.29
     only
    0.27
    åıªæľī
    0.27
    åıªçŁ¥éģĵ
    0.26
    çħ
    0.25
    åıªä¼ļ
    0.24
     solely
    0.24
    åįķä¸Ģ
    0.24
    .Today
    0.23
    å±ĢéĻIJäºİ
    0.23
    Activations Density 0.238%

    No Known Activations