© 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. 10611
    Prev
    Next
    INDEX
    Explanations

    living beings and species

    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
    çĺª
    -0.21
    缩
    -0.20
    建æĪIJåIJİ
    -0.20
    å©ļåIJİ
    -0.20
     Äijám
    -0.19
    åĽ½éĻħåĮĸ
    -0.19
    æĺİ亮
    -0.19
    æĴ¤
    -0.19
    æ²ī积
    -0.19
    otch
    -0.19
    POSITIVE LOGITS
     creatures
    0.21
    æľĭåıĭ
    0.20
     animals
    0.20
    åħ±äº«
    0.20
     species
    0.20
    éĨ¢
    0.20
    享æľī
    0.19
     living
    0.19
    ä¼Ļä¼´
    0.19
     bending
    0.19
    Activations Density 0.012%

    No Known Activations