© 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. 14448
    Prev
    Next
    INDEX
    Explanations

    most common/frequent/greatest

    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
    个ä½ĵ
    -0.19
    éĢĤåIJĪèĩªå·±
    -0.19
    缴è¾ĸå¸Ĥ
    -0.19
    鸣
    -0.19
    ä¹Łä¸įéĶĻ
    -0.19
    mı
    -0.19
    aten
    -0.19
    иÑĢÑĥ
    -0.19
    æĺ¥å¤ı
    -0.18
    elib
    -0.18
    POSITIVE LOGITS
    ä¸Ģ项
    0.26
    æĺ¯ä¸Ģ项
    0.23
    ä»ħ次äºİ
    0.21
    Rp
    0.21
     Joyce
    0.20
    ä¸ĢéŨ
    0.20
    åĵī
    0.20
    æĶ¸
    0.19
     subsystem
    0.19
    被åĪĹåħ¥
    0.19
    Activations Density 0.380%

    No Known Activations