© 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. 16499
    Prev
    Next
    INDEX
    Explanations

    USB cable connection

    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
    lobber
    -0.20
    äºĮ次
    -0.20
     replacements
    -0.19
    æĺİå¹´
    -0.19
    èIJ½ä¸ĭ
    -0.19
    缺失
    -0.18
    äºĶ大
    -0.18
    åįķ项
    -0.18
    OfYear
    -0.18
    _ARROW
    -0.18
    POSITIVE LOGITS
    Wik
    0.22
    çİĽä¸½
    0.21
    æĬ¤èº«
    0.20
    åı¯çĶ¨äºİ
    0.20
     Corpus
    0.20
     Florian
    0.20
     Mir
    0.20
    æľīä¸ĢçĤ¹
    0.19
     tran
    0.19
    stellar
    0.19
    Activations Density 0.005%

    No Known Activations