© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16961
    Prev
    Next
    INDEX
    Explanations

    famous people and groups

    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
    ä¼ŀ
    -0.21
    .ali
    -0.20
    Writable
    -0.19
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.19
    帡
    -0.18
    éľĦ
    -0.18
    ä¸Ģç»Ħ
    -0.17
     cumulative
    -0.17
    çĪ±åĽ½ä¸»ä¹ī
    -0.17
    ooter
    -0.17
    POSITIVE LOGITS
    ëĥ¥
    0.20
     Jungle
    0.19
    æŶè£ħ
    0.19
    æł·çļĦ
    0.18
    oman
    0.18
    æŁĶ
    0.18
    æĤĸ
    0.18
    omon
    0.18
    ä¸įåĪĨ
    0.18
     Ñģпин
    0.18
    Activations Density 0.016%

    No Known Activations