© 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. 15014
    Prev
    Next
    INDEX
    Explanations

    pheresis, ectomy, vascular, construct, phosphate

    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
     striking
    -0.21
    isure
    -0.19
    åı£æ°´
    -0.19
    çīĩ
    -0.19
    åįıä¼ļä¼ļåijĺ
    -0.18
    .Configuration
    -0.18
    ä¸ĵåįĸåºĹ
    -0.18
    åħħå®ŀ
    -0.18
     Extension
    -0.17
     Mens
    -0.17
    POSITIVE LOGITS
    çĶij
    0.21
    åѬ
    0.20
    åı¯çĶ¨äºİ
    0.20
    æģĻ
    0.19
    imity
    0.19
    nia
    0.19
    æ¡¢
    0.19
    .firebase
    0.19
    è²Į
    0.18
    æĥ¯ä¾ĭ
    0.18
    Activations Density 0.529%

    No Known Activations